{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 21010,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.9490705132484436,
      "learning_rate": 9.932255753356769e-05,
      "loss": 0.8036,
      "step": 2101
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5146420001983643,
      "learning_rate": 9.398649562950904e-05,
      "loss": 0.2873,
      "step": 4202
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.8661231994628906,
      "learning_rate": 8.388357776018592e-05,
      "loss": 0.1842,
      "step": 6303
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.0393620729446411,
      "learning_rate": 7.011587153401483e-05,
      "loss": 0.1351,
      "step": 8404
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.3505756855010986,
      "learning_rate": 5.4170246035912365e-05,
      "loss": 0.1071,
      "step": 10505
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.32957354187965393,
      "learning_rate": 3.776548239300111e-05,
      "loss": 0.0902,
      "step": 12606
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.22965189814567566,
      "learning_rate": 2.2686584391405702e-05,
      "loss": 0.0798,
      "step": 14707
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.38085827231407166,
      "learning_rate": 1.0572505128335552e-05,
      "loss": 0.073,
      "step": 16808
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.45917150378227234,
      "learning_rate": 2.7271895019674864e-06,
      "loss": 0.0683,
      "step": 18909
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.3299286961555481,
      "learning_rate": 3.964077296414459e-11,
      "loss": 0.065,
      "step": 21010
    }
  ],
  "logging_steps": 500,
  "max_steps": 21010,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1512256905838592e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}