{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014776505356483192,
  "eval_steps": 8,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014776505356483192,
      "eval_loss": 2.284550189971924,
      "eval_runtime": 8.0244,
      "eval_samples_per_second": 35.517,
      "eval_steps_per_second": 17.821,
      "step": 1
    },
    {
      "epoch": 0.004432951606944958,
      "grad_norm": 1.086187481880188,
      "learning_rate": 6e-05,
      "loss": 2.246,
      "step": 3
    },
    {
      "epoch": 0.008865903213889916,
      "grad_norm": 0.9703373908996582,
      "learning_rate": 0.00012,
      "loss": 2.3058,
      "step": 6
    },
    {
      "epoch": 0.011821204285186553,
      "eval_loss": 2.1647727489471436,
      "eval_runtime": 6.9073,
      "eval_samples_per_second": 41.261,
      "eval_steps_per_second": 20.703,
      "step": 8
    },
    {
      "epoch": 0.013298854820834873,
      "grad_norm": 1.1059170961380005,
      "learning_rate": 0.00018,
      "loss": 2.2392,
      "step": 9
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 653134418411520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}