{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0701877522372346,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01403755044744692,
      "grad_norm": 2.182603597640991,
      "learning_rate": 4.936666666666667e-05,
      "loss": 1.0775,
      "mean_token_accuracy": 0.7353726878762246,
      "num_tokens": 21541.0,
      "step": 20
    },
    {
      "epoch": 0.02807510089489384,
      "grad_norm": 1.6199620962142944,
      "learning_rate": 4.87e-05,
      "loss": 0.831,
      "mean_token_accuracy": 0.7886073857545852,
      "num_tokens": 41741.0,
      "step": 40
    },
    {
      "epoch": 0.04211265134234076,
      "grad_norm": 1.5445266962051392,
      "learning_rate": 4.803333333333333e-05,
      "loss": 0.8208,
      "mean_token_accuracy": 0.7912300959229469,
      "num_tokens": 64250.0,
      "step": 60
    },
    {
      "epoch": 0.05615020178978768,
      "grad_norm": 3.0431602001190186,
      "learning_rate": 4.736666666666667e-05,
      "loss": 0.7495,
      "mean_token_accuracy": 0.8050705902278423,
      "num_tokens": 82180.0,
      "step": 80
    },
    {
      "epoch": 0.0701877522372346,
      "grad_norm": 2.468738555908203,
      "learning_rate": 4.6700000000000003e-05,
      "loss": 0.6958,
      "mean_token_accuracy": 0.8200091950595378,
      "num_tokens": 103406.0,
      "step": 100
    }
  ],
  "logging_steps": 20,
  "max_steps": 1500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4413828956405760.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}