{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.347593582887701,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6557157039642334,
      "eval_loss": 0.5895818471908569,
      "eval_runtime": 14.1651,
      "eval_samples_per_second": 210.588,
      "eval_steps_per_second": 13.201,
      "step": 187
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6775058507919312,
      "eval_loss": 0.560325026512146,
      "eval_runtime": 13.2773,
      "eval_samples_per_second": 224.67,
      "eval_steps_per_second": 14.084,
      "step": 374
    },
    {
      "epoch": 2.6737967914438503,
      "grad_norm": 7.770582675933838,
      "learning_rate": 1.736336286304512e-05,
      "loss": 0.566,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6842105388641357,
      "eval_loss": 0.5659032464027405,
      "eval_runtime": 16.7775,
      "eval_samples_per_second": 177.797,
      "eval_steps_per_second": 11.146,
      "step": 561
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6932618021965027,
      "eval_loss": 0.6125087141990662,
      "eval_runtime": 16.7549,
      "eval_samples_per_second": 178.038,
      "eval_steps_per_second": 11.161,
      "step": 748
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6982902884483337,
      "eval_loss": 0.649093747138977,
      "eval_runtime": 18.0748,
      "eval_samples_per_second": 165.036,
      "eval_steps_per_second": 10.346,
      "step": 935
    },
    {
      "epoch": 5.347593582887701,
      "grad_norm": 15.092613220214844,
      "learning_rate": 1.1026369117408215e-05,
      "loss": 0.3717,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 1870,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3102926121226212.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 2.3700356608682024e-05,
    "per_device_train_batch_size": 64
  }
}