{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.45791245791245794,
  "eval_steps": 500,
  "global_step": 34,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13468013468013468,
      "grad_norm": 18.875,
      "learning_rate": 4.875778746747527e-07,
      "loss": 2.2397235870361327,
      "step": 10
    },
    {
      "epoch": 0.26936026936026936,
      "grad_norm": 7.65625,
      "learning_rate": 2.480452864093708e-07,
      "loss": 2.2770544052124024,
      "step": 20
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 8.5,
      "learning_rate": 3.2471652304202396e-08,
      "loss": 2.0806552886962892,
      "step": 30
    },
    {
      "epoch": 0.45791245791245794,
      "step": 34,
      "total_flos": 1.6323997048246272e+16,
      "train_loss": 2.228161503286923,
      "train_runtime": 271.7669,
      "train_samples_per_second": 0.492,
      "train_steps_per_second": 0.125
    }
  ],
  "logging_steps": 10,
  "max_steps": 34,
  "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": 1.6323997048246272e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}