{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 42,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8955223880597015,
      "grad_norm": 0.902472804072769,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.932,
      "mean_token_accuracy": 0.807638356089592,
      "num_tokens": 9406298.0,
      "step": 5
    },
    {
      "epoch": 1.716417910447761,
      "grad_norm": 0.47865190707110405,
      "learning_rate": 1.783783783783784e-05,
      "loss": 0.714,
      "mean_token_accuracy": 0.8429910551417957,
      "num_tokens": 17339132.0,
      "step": 10
    },
    {
      "epoch": 2.5373134328358207,
      "grad_norm": 0.29869720168197184,
      "learning_rate": 1.5135135135135138e-05,
      "loss": 0.6167,
      "mean_token_accuracy": 0.8631752198392695,
      "num_tokens": 25334534.0,
      "step": 15
    },
    {
      "epoch": 3.3582089552238807,
      "grad_norm": 0.17316175867981973,
      "learning_rate": 1.2432432432432433e-05,
      "loss": 0.5426,
      "mean_token_accuracy": 0.8763437249443747,
      "num_tokens": 33275501.0,
      "step": 20
    },
    {
      "epoch": 4.17910447761194,
      "grad_norm": 0.17983013768425976,
      "learning_rate": 9.729729729729732e-06,
      "loss": 0.5497,
      "mean_token_accuracy": 0.877435192194852,
      "num_tokens": 41225062.0,
      "step": 25
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.22514151865077917,
      "learning_rate": 7.027027027027028e-06,
      "loss": 0.5304,
      "mean_token_accuracy": 0.8791955297643488,
      "num_tokens": 49232938.0,
      "step": 30
    },
    {
      "epoch": 5.895522388059701,
      "grad_norm": 0.1277724205532296,
      "learning_rate": 4.324324324324325e-06,
      "loss": 0.5219,
      "mean_token_accuracy": 0.8798246135314306,
      "num_tokens": 58665081.0,
      "step": 35
    },
    {
      "epoch": 6.7164179104477615,
      "grad_norm": 0.11964903825154485,
      "learning_rate": 1.6216216216216219e-06,
      "loss": 0.4844,
      "mean_token_accuracy": 0.8860228516838767,
      "num_tokens": 66624412.0,
      "step": 40
    },
    {
      "epoch": 7.0,
      "mean_token_accuracy": 0.8833393893743816,
      "num_tokens": 68894483.0,
      "step": 42,
      "total_flos": 106682420035584.0,
      "train_loss": 0.6058833613282159,
      "train_runtime": 1066.5874,
      "train_samples_per_second": 3.485,
      "train_steps_per_second": 0.039
    }
  ],
  "logging_steps": 5,
  "max_steps": 42,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 106682420035584.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}