{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.6,
  "eval_steps": 500,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15,
      "grad_norm": 35.73806381225586,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 3.2839,
      "step": 1
    },
    {
      "epoch": 0.3,
      "grad_norm": 35.236732482910156,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 3.2281,
      "step": 2
    },
    {
      "epoch": 0.45,
      "grad_norm": 35.85063171386719,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 3.2521,
      "step": 3
    },
    {
      "epoch": 0.6,
      "grad_norm": 35.62168884277344,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 3.2824,
      "step": 4
    },
    {
      "epoch": 0.75,
      "grad_norm": 36.429351806640625,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 3.3533,
      "step": 5
    },
    {
      "epoch": 0.9,
      "grad_norm": 36.30988311767578,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 3.3279,
      "step": 6
    },
    {
      "epoch": 1.0,
      "grad_norm": 36.30988311767578,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 3.2644,
      "step": 7
    },
    {
      "epoch": 1.15,
      "grad_norm": 46.94998550415039,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 3.2235,
      "step": 8
    },
    {
      "epoch": 1.3,
      "grad_norm": 36.432373046875,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 3.1799,
      "step": 9
    },
    {
      "epoch": 1.45,
      "grad_norm": 36.3123779296875,
      "learning_rate": 5.000000000000001e-07,
      "loss": 3.1618,
      "step": 10
    },
    {
      "epoch": 1.6,
      "grad_norm": 34.80661392211914,
      "learning_rate": 5.5e-07,
      "loss": 3.1557,
      "step": 11
    },
    {
      "epoch": 1.75,
      "grad_norm": 36.64874267578125,
      "learning_rate": 6.000000000000001e-07,
      "loss": 3.1375,
      "step": 12
    },
    {
      "epoch": 1.9,
      "grad_norm": 36.32555389404297,
      "learning_rate": 6.5e-07,
      "loss": 3.0565,
      "step": 13
    },
    {
      "epoch": 2.0,
      "grad_norm": 47.40998077392578,
      "learning_rate": 7.000000000000001e-07,
      "loss": 3.0395,
      "step": 14
    },
    {
      "epoch": 2.15,
      "grad_norm": 37.59382629394531,
      "learning_rate": 7.5e-07,
      "loss": 2.8641,
      "step": 15
    },
    {
      "epoch": 2.3,
      "grad_norm": 36.185447692871094,
      "learning_rate": 8.000000000000001e-07,
      "loss": 2.87,
      "step": 16
    },
    {
      "epoch": 2.45,
      "grad_norm": 36.60142135620117,
      "learning_rate": 8.500000000000001e-07,
      "loss": 2.6385,
      "step": 17
    },
    {
      "epoch": 2.6,
      "grad_norm": 34.09886169433594,
      "learning_rate": 9.000000000000001e-07,
      "loss": 2.5288,
      "step": 18
    }
  ],
  "logging_steps": 1,
  "max_steps": 36,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 6,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1043631369342157e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}