{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0039670732916790635,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00039670732916790636,
      "grad_norm": 20.232769012451172,
      "learning_rate": 2e-05,
      "loss": 16.5819,
      "step": 1
    },
    {
      "epoch": 0.00039670732916790636,
      "eval_loss": 3.460477352142334,
      "eval_runtime": 7.9562,
      "eval_samples_per_second": 133.481,
      "eval_steps_per_second": 66.741,
      "step": 1
    },
    {
      "epoch": 0.0007934146583358127,
      "grad_norm": 21.32288360595703,
      "learning_rate": 4e-05,
      "loss": 16.1027,
      "step": 2
    },
    {
      "epoch": 0.0011901219875037191,
      "grad_norm": 22.184568405151367,
      "learning_rate": 6e-05,
      "loss": 14.998,
      "step": 3
    },
    {
      "epoch": 0.0011901219875037191,
      "eval_loss": 3.4389564990997314,
      "eval_runtime": 7.1502,
      "eval_samples_per_second": 148.527,
      "eval_steps_per_second": 74.263,
      "step": 3
    },
    {
      "epoch": 0.0015868293166716254,
      "grad_norm": 22.865812301635742,
      "learning_rate": 8e-05,
      "loss": 15.7034,
      "step": 4
    },
    {
      "epoch": 0.0019835366458395317,
      "grad_norm": 18.588085174560547,
      "learning_rate": 0.0001,
      "loss": 13.4016,
      "step": 5
    },
    {
      "epoch": 0.0023802439750074383,
      "grad_norm": 16.03754997253418,
      "learning_rate": 0.00012,
      "loss": 13.8681,
      "step": 6
    },
    {
      "epoch": 0.0023802439750074383,
      "eval_loss": 3.2986671924591064,
      "eval_runtime": 7.1676,
      "eval_samples_per_second": 148.167,
      "eval_steps_per_second": 74.083,
      "step": 6
    },
    {
      "epoch": 0.002776951304175345,
      "grad_norm": 16.274703979492188,
      "learning_rate": 0.00014,
      "loss": 14.4237,
      "step": 7
    },
    {
      "epoch": 0.003173658633343251,
      "grad_norm": 14.675177574157715,
      "learning_rate": 0.00016,
      "loss": 11.0826,
      "step": 8
    },
    {
      "epoch": 0.0035703659625111574,
      "grad_norm": 21.122060775756836,
      "learning_rate": 0.00018,
      "loss": 12.2096,
      "step": 9
    },
    {
      "epoch": 0.0035703659625111574,
      "eval_loss": 3.0325326919555664,
      "eval_runtime": 7.2932,
      "eval_samples_per_second": 145.615,
      "eval_steps_per_second": 72.807,
      "step": 9
    },
    {
      "epoch": 0.0039670732916790635,
      "grad_norm": 16.79721450805664,
      "learning_rate": 0.0002,
      "loss": 13.2189,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 27067627339776.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}