{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 270,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 2.8517868518829346,
      "learning_rate": 1.6370370370370374e-05,
      "loss": 0.4408,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9459459459459459,
      "eval_loss": 0.1763220876455307,
      "eval_runtime": 0.5083,
      "eval_samples_per_second": 1747.017,
      "eval_steps_per_second": 55.086,
      "step": 54
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 1.7455177307128906,
      "learning_rate": 1.2666666666666667e-05,
      "loss": 0.1407,
      "step": 100
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9628378378378378,
      "eval_loss": 0.1221194714307785,
      "eval_runtime": 0.6023,
      "eval_samples_per_second": 1474.32,
      "eval_steps_per_second": 46.488,
      "step": 108
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 3.1013050079345703,
      "learning_rate": 8.962962962962963e-06,
      "loss": 0.0762,
      "step": 150
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.963963963963964,
      "eval_loss": 0.11229722201824188,
      "eval_runtime": 0.6443,
      "eval_samples_per_second": 1378.158,
      "eval_steps_per_second": 43.455,
      "step": 162
    },
    {
      "epoch": 3.7037037037037037,
      "grad_norm": 1.3716905117034912,
      "learning_rate": 5.259259259259259e-06,
      "loss": 0.0563,
      "step": 200
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9718468468468469,
      "eval_loss": 0.12264640629291534,
      "eval_runtime": 0.6481,
      "eval_samples_per_second": 1370.16,
      "eval_steps_per_second": 43.203,
      "step": 216
    },
    {
      "epoch": 4.62962962962963,
      "grad_norm": 0.5899084806442261,
      "learning_rate": 1.5555555555555558e-06,
      "loss": 0.0423,
      "step": 250
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9662162162162162,
      "eval_loss": 0.1229998990893364,
      "eval_runtime": 0.6595,
      "eval_samples_per_second": 1346.563,
      "eval_steps_per_second": 42.459,
      "step": 270
    },
    {
      "epoch": 5.0,
      "step": 270,
      "total_flos": 4546681584484352.0,
      "train_loss": 0.1416260372709345,
      "train_runtime": 63.0434,
      "train_samples_per_second": 547.242,
      "train_steps_per_second": 4.283
    }
  ],
  "logging_steps": 50,
  "max_steps": 270,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 4546681584484352.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}