{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 2114,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.23651844843897823,
      "grad_norm": 0.62890625,
      "learning_rate": 1.881740775780511e-05,
      "loss": 0.1514,
      "mean_token_accuracy": 0.9655648044347763,
      "step": 500
    },
    {
      "epoch": 0.47303689687795647,
      "grad_norm": 0.6796875,
      "learning_rate": 1.763481551561022e-05,
      "loss": 0.0923,
      "mean_token_accuracy": 0.9776788552999497,
      "step": 1000
    },
    {
      "epoch": 0.7095553453169348,
      "grad_norm": 1.296875,
      "learning_rate": 1.6452223273415328e-05,
      "loss": 0.085,
      "mean_token_accuracy": 0.9792790929079056,
      "step": 1500
    },
    {
      "epoch": 0.9460737937559129,
      "grad_norm": 0.6171875,
      "learning_rate": 1.5269631031220437e-05,
      "loss": 0.0811,
      "mean_token_accuracy": 0.9799440746307373,
      "step": 2000
    }
  ],
  "logging_steps": 500,
  "max_steps": 8456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3429509315661824e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}