{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 8,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.125,
      "grad_norm": 11.490795933276278,
      "learning_rate": 1e-05,
      "loss": 0.4599,
      "step": 1
    },
    {
      "epoch": 0.25,
      "grad_norm": 12.478241892988105,
      "learning_rate": 9.504844339512096e-06,
      "loss": 0.4918,
      "step": 2
    },
    {
      "epoch": 0.375,
      "grad_norm": 4.49559329385041,
      "learning_rate": 8.117449009293668e-06,
      "loss": 0.2563,
      "step": 3
    },
    {
      "epoch": 0.5,
      "grad_norm": 4.424673058399549,
      "learning_rate": 6.112604669781572e-06,
      "loss": 0.2139,
      "step": 4
    },
    {
      "epoch": 0.625,
      "grad_norm": 2.9014709164107373,
      "learning_rate": 3.887395330218429e-06,
      "loss": 0.2348,
      "step": 5
    },
    {
      "epoch": 0.75,
      "grad_norm": 4.076222631002798,
      "learning_rate": 1.8825509907063328e-06,
      "loss": 0.2312,
      "step": 6
    },
    {
      "epoch": 0.875,
      "grad_norm": 2.9888598100641968,
      "learning_rate": 4.951556604879049e-07,
      "loss": 0.2458,
      "step": 7
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.542613251786923,
      "learning_rate": 0.0,
      "loss": 0.2089,
      "step": 8
    },
    {
      "epoch": 1.0,
      "step": 8,
      "total_flos": 1479350042624.0,
      "train_loss": 0.2928274031728506,
      "train_runtime": 62.0168,
      "train_samples_per_second": 16.512,
      "train_steps_per_second": 0.129
    }
  ],
  "logging_steps": 1,
  "max_steps": 8,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1479350042624.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}