{
  "best_global_step": 200,
  "best_metric": 0.6018396615982056,
  "best_model_checkpoint": "./t5gemma-math-corrector/checkpoint-200",
  "epoch": 0.6415396952686447,
  "eval_steps": 200,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16038492381716118,
      "grad_norm": 2.080294370651245,
      "learning_rate": 5.212765957446809e-05,
      "loss": 1.8373,
      "step": 50
    },
    {
      "epoch": 0.32076984763432237,
      "grad_norm": 1.3640859127044678,
      "learning_rate": 9.94061757719715e-05,
      "loss": 0.028,
      "step": 100
    },
    {
      "epoch": 0.48115477145148355,
      "grad_norm": 0.47297751903533936,
      "learning_rate": 9.346793349168646e-05,
      "loss": 0.0138,
      "step": 150
    },
    {
      "epoch": 0.6415396952686447,
      "grad_norm": 0.6050183176994324,
      "learning_rate": 8.752969121140144e-05,
      "loss": 0.0085,
      "step": 200
    },
    {
      "epoch": 0.6415396952686447,
      "eval_loss": 0.6018396615982056,
      "eval_runtime": 5.1929,
      "eval_samples_per_second": 50.454,
      "eval_steps_per_second": 12.71,
      "step": 200
    }
  ],
  "logging_steps": 50,
  "max_steps": 936,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 773230008729600.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}