{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0027532092094848058,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005506418418969612,
      "grad_norm": 3.038654327392578,
      "learning_rate": 1e-05,
      "loss": 9.3534,
      "step": 1
    },
    {
      "epoch": 0.0005506418418969612,
      "eval_loss": 10.285574913024902,
      "eval_runtime": 106.3739,
      "eval_samples_per_second": 28.757,
      "eval_steps_per_second": 14.383,
      "step": 1
    },
    {
      "epoch": 0.0011012836837939223,
      "grad_norm": 2.8653018474578857,
      "learning_rate": 2e-05,
      "loss": 8.8957,
      "step": 2
    },
    {
      "epoch": 0.0011012836837939223,
      "eval_loss": 10.242318153381348,
      "eval_runtime": 41.2934,
      "eval_samples_per_second": 74.08,
      "eval_steps_per_second": 37.052,
      "step": 2
    },
    {
      "epoch": 0.0016519255256908835,
      "grad_norm": 3.079319715499878,
      "learning_rate": 3e-05,
      "loss": 9.1464,
      "step": 3
    },
    {
      "epoch": 0.0022025673675878446,
      "grad_norm": 2.831951856613159,
      "learning_rate": 4e-05,
      "loss": 9.138,
      "step": 4
    },
    {
      "epoch": 0.0022025673675878446,
      "eval_loss": 10.193074226379395,
      "eval_runtime": 41.3621,
      "eval_samples_per_second": 73.957,
      "eval_steps_per_second": 36.99,
      "step": 4
    },
    {
      "epoch": 0.0027532092094848058,
      "grad_norm": 3.16037917137146,
      "learning_rate": 5e-05,
      "loss": 9.8383,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 133741336854528.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}