{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 29,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 112.91146087646484,
      "learning_rate": 8.43120818934367e-05,
      "loss": 178.4693359375,
      "step": 10
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 69.01692962646484,
      "learning_rate": 3.019601169804216e-05,
      "loss": 143.72413330078126,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_loss": 8.519869804382324,
      "eval_runtime": 12.6349,
      "eval_samples_per_second": 3.166,
      "eval_steps_per_second": 3.166,
      "step": 29
    },
    {
      "epoch": 1.0,
      "step": 29,
      "total_flos": 2.9686113589837824e+16,
      "train_loss": 151.82884058459052,
      "train_runtime": 802.9271,
      "train_samples_per_second": 0.573,
      "train_steps_per_second": 0.036
    }
  ],
  "logging_steps": 10,
  "max_steps": 29,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.9686113589837824e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}