{
  "best_global_step": 50,
  "best_metric": 1.071570634841919,
  "best_model_checkpoint": "/data/output/checkpoint-50",
  "epoch": 0.1707941929974381,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.1713112026453019,
      "epoch": 0.034158838599487616,
      "grad_norm": 3.3329014778137207,
      "learning_rate": 0.00012,
      "loss": 1.2999439239501953,
      "mean_token_accuracy": 0.6959523037075996,
      "num_tokens": 643010.0,
      "step": 10
    },
    {
      "entropy": 1.1543982975184917,
      "epoch": 0.06831767719897523,
      "grad_norm": 2.581118106842041,
      "learning_rate": 0.00019989785286500295,
      "loss": 1.1518776893615723,
      "mean_token_accuracy": 0.7155417971313,
      "num_tokens": 1251488.0,
      "step": 20
    },
    {
      "entropy": 0.9459363672882318,
      "epoch": 0.10247651579846286,
      "grad_norm": 2.3779942989349365,
      "learning_rate": 0.00019875109281794825,
      "loss": 0.9381013870239258,
      "mean_token_accuracy": 0.7682368114590645,
      "num_tokens": 1696074.0,
      "step": 30
    },
    {
      "entropy": 0.9385578982532025,
      "epoch": 0.13663535439795046,
      "grad_norm": 2.0882723331451416,
      "learning_rate": 0.00019634456691705702,
      "loss": 0.9547281265258789,
      "mean_token_accuracy": 0.7626850850880146,
      "num_tokens": 2006643.0,
      "step": 40
    },
    {
      "entropy": 0.9006230250000954,
      "epoch": 0.1707941929974381,
      "grad_norm": 2.151762008666992,
      "learning_rate": 0.00019270897516847403,
      "loss": 0.9329019546508789,
      "mean_token_accuracy": 0.7718432284891605,
      "num_tokens": 2177826.0,
      "step": 50
    },
    {
      "epoch": 0.1707941929974381,
      "eval_entropy": 1.0149640817940235,
      "eval_loss": 1.071570634841919,
      "eval_mean_token_accuracy": 0.742358745932579,
      "eval_num_tokens": 2177826.0,
      "eval_runtime": 95.085,
      "eval_samples_per_second": 1.052,
      "eval_steps_per_second": 1.052,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 293,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.41512647094272e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}