{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16901408450704225,
  "eval_steps": 500,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.028169014084507043,
      "grad_norm": 0.3046221137046814,
      "learning_rate": 1e-08,
      "loss": 0.7936,
      "mean_token_accuracy": 0.8673804849386215,
      "step": 1
    },
    {
      "epoch": 0.056338028169014086,
      "grad_norm": 0.31545570492744446,
      "learning_rate": 2e-08,
      "loss": 0.7759,
      "mean_token_accuracy": 0.8740345686674118,
      "step": 2
    },
    {
      "epoch": 0.08450704225352113,
      "grad_norm": 0.25415748357772827,
      "learning_rate": 3.0000000000000004e-08,
      "loss": 0.6719,
      "mean_token_accuracy": 0.8830722570419312,
      "step": 3
    },
    {
      "epoch": 0.11267605633802817,
      "grad_norm": 0.3462650179862976,
      "learning_rate": 4e-08,
      "loss": 0.8779,
      "mean_token_accuracy": 0.8565912544727325,
      "step": 4
    },
    {
      "epoch": 0.14084507042253522,
      "grad_norm": 0.28566086292266846,
      "learning_rate": 3.98973864678379e-08,
      "loss": 0.7654,
      "mean_token_accuracy": 0.8742299824953079,
      "step": 5
    },
    {
      "epoch": 0.16901408450704225,
      "grad_norm": 0.2303602248430252,
      "learning_rate": 3.959059882504989e-08,
      "loss": 0.6373,
      "mean_token_accuracy": 0.8818237036466599,
      "step": 6
    }
  ],
  "logging_steps": 1,
  "max_steps": 35,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 804264308170752.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}