{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 129,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.44545748829841614,
      "learning_rate": 7.6e-05,
      "loss": 0.687,
      "step": 20
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.3853379189968109,
      "learning_rate": 0.00015600000000000002,
      "loss": 0.6039,
      "step": 40
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.4913628101348877,
      "learning_rate": 0.00017721518987341773,
      "loss": 0.4516,
      "step": 60
    },
    {
      "epoch": 1.8705882352941177,
      "grad_norm": 0.7104933261871338,
      "learning_rate": 0.00012658227848101267,
      "loss": 0.4665,
      "step": 80
    },
    {
      "epoch": 2.3294117647058825,
      "grad_norm": 0.3440960645675659,
      "learning_rate": 7.59493670886076e-05,
      "loss": 0.3683,
      "step": 100
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.470425546169281,
      "learning_rate": 2.5316455696202533e-05,
      "loss": 0.3161,
      "step": 120
    }
  ],
  "logging_steps": 20,
  "max_steps": 129,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.1761705519193088e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}