{
  "best_global_step": 200,
  "best_metric": 4.437816143035889,
  "best_model_checkpoint": "./t5gemma-math-corrector/checkpoint-200",
  "epoch": 3.0,
  "eval_steps": 200,
  "global_step": 888,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1693480101608806,
      "grad_norm": 1.3522921800613403,
      "learning_rate": 5.50561797752809e-05,
      "loss": 2.2844,
      "step": 50
    },
    {
      "epoch": 0.3386960203217612,
      "grad_norm": 0.5189423561096191,
      "learning_rate": 9.874843554443054e-05,
      "loss": 0.0374,
      "step": 100
    },
    {
      "epoch": 0.5080440304826418,
      "grad_norm": 0.2796284258365631,
      "learning_rate": 9.249061326658323e-05,
      "loss": 0.0167,
      "step": 150
    },
    {
      "epoch": 0.6773920406435224,
      "grad_norm": 0.5644184350967407,
      "learning_rate": 8.623279098873592e-05,
      "loss": 0.0108,
      "step": 200
    },
    {
      "epoch": 0.6773920406435224,
      "eval_loss": 4.437816143035889,
      "eval_runtime": 10.3595,
      "eval_samples_per_second": 50.582,
      "eval_steps_per_second": 12.645,
      "step": 200
    },
    {
      "epoch": 0.8467400508044031,
      "grad_norm": 0.395366907119751,
      "learning_rate": 7.997496871088861e-05,
      "loss": 0.0073,
      "step": 250
    },
    {
      "epoch": 1.0135478408128704,
      "grad_norm": 0.14810292422771454,
      "learning_rate": 7.371714643304131e-05,
      "loss": 0.0079,
      "step": 300
    },
    {
      "epoch": 1.182895850973751,
      "grad_norm": 0.2394929677248001,
      "learning_rate": 6.7459324155194e-05,
      "loss": 0.0039,
      "step": 350
    },
    {
      "epoch": 1.3522438611346317,
      "grad_norm": 0.4444918930530548,
      "learning_rate": 6.120150187734669e-05,
      "loss": 0.0034,
      "step": 400
    },
    {
      "epoch": 1.3522438611346317,
      "eval_loss": 7.077005863189697,
      "eval_runtime": 10.3846,
      "eval_samples_per_second": 50.459,
      "eval_steps_per_second": 12.615,
      "step": 400
    },
    {
      "epoch": 1.5215918712955123,
      "grad_norm": 0.19818231463432312,
      "learning_rate": 5.4943679599499376e-05,
      "loss": 0.0026,
      "step": 450
    },
    {
      "epoch": 1.690939881456393,
      "grad_norm": 0.21913927793502808,
      "learning_rate": 4.8685857321652064e-05,
      "loss": 0.0027,
      "step": 500
    },
    {
      "epoch": 1.8602878916172734,
      "grad_norm": 0.10620615631341934,
      "learning_rate": 4.242803504380476e-05,
      "loss": 0.0025,
      "step": 550
    },
    {
      "epoch": 2.027095681625741,
      "grad_norm": 0.03891622647643089,
      "learning_rate": 3.617021276595745e-05,
      "loss": 0.002,
      "step": 600
    },
    {
      "epoch": 2.027095681625741,
      "eval_loss": 7.624501705169678,
      "eval_runtime": 10.3997,
      "eval_samples_per_second": 50.386,
      "eval_steps_per_second": 12.597,
      "step": 600
    },
    {
      "epoch": 2.1964436917866217,
      "grad_norm": 0.05978698655962944,
      "learning_rate": 2.9912390488110137e-05,
      "loss": 0.0012,
      "step": 650
    },
    {
      "epoch": 2.365791701947502,
      "grad_norm": 0.04675230383872986,
      "learning_rate": 2.365456821026283e-05,
      "loss": 0.0011,
      "step": 700
    },
    {
      "epoch": 2.535139712108383,
      "grad_norm": 0.056206703186035156,
      "learning_rate": 1.739674593241552e-05,
      "loss": 0.001,
      "step": 750
    },
    {
      "epoch": 2.7044877222692634,
      "grad_norm": 0.11963123828172684,
      "learning_rate": 1.113892365456821e-05,
      "loss": 0.0011,
      "step": 800
    },
    {
      "epoch": 2.7044877222692634,
      "eval_loss": 7.175710201263428,
      "eval_runtime": 10.392,
      "eval_samples_per_second": 50.423,
      "eval_steps_per_second": 12.606,
      "step": 800
    },
    {
      "epoch": 2.873835732430144,
      "grad_norm": 0.19036388397216797,
      "learning_rate": 4.881101376720902e-06,
      "loss": 0.0012,
      "step": 850
    }
  ],
  "logging_steps": 50,
  "max_steps": 888,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3379504493887488.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}