{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16835016835016836,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003367003367003367,
      "eval_loss": 0.27984634041786194,
      "eval_runtime": 6.4498,
      "eval_samples_per_second": 19.38,
      "eval_steps_per_second": 9.768,
      "step": 1
    },
    {
      "epoch": 0.03367003367003367,
      "grad_norm": 0.02833857573568821,
      "learning_rate": 0.0002,
      "loss": 0.0902,
      "step": 10
    },
    {
      "epoch": 0.06734006734006734,
      "grad_norm": 0.0009272642200812697,
      "learning_rate": 0.0002,
      "loss": 0.0001,
      "step": 20
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 0.0006098205922171474,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.13468013468013468,
      "grad_norm": 0.0002674128918442875,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.16835016835016836,
      "grad_norm": 0.00012873827654402703,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.16835016835016836,
      "eval_loss": 3.838794327748474e-06,
      "eval_runtime": 5.0581,
      "eval_samples_per_second": 24.713,
      "eval_steps_per_second": 12.455,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "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": 1.0560913539072e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}