{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.1052631578947367,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 1.1066950559616089,
      "learning_rate": 1e-05,
      "loss": 177.125,
      "step": 1
    },
    {
      "epoch": 0.21052631578947367,
      "eval_loss": 11.078125,
      "eval_runtime": 6.2325,
      "eval_samples_per_second": 1.284,
      "eval_steps_per_second": 0.642,
      "step": 1
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 1.1763187646865845,
      "learning_rate": 2e-05,
      "loss": 177.1875,
      "step": 2
    },
    {
      "epoch": 0.42105263157894735,
      "eval_loss": 11.078125,
      "eval_runtime": 0.0447,
      "eval_samples_per_second": 178.823,
      "eval_steps_per_second": 89.412,
      "step": 2
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 1.167242169380188,
      "learning_rate": 3e-05,
      "loss": 177.1875,
      "step": 3
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 1.0927841663360596,
      "learning_rate": 4e-05,
      "loss": 177.0625,
      "step": 4
    },
    {
      "epoch": 0.8421052631578947,
      "eval_loss": 11.078125,
      "eval_runtime": 0.0442,
      "eval_samples_per_second": 181.029,
      "eval_steps_per_second": 90.514,
      "step": 4
    },
    {
      "epoch": 1.1052631578947367,
      "grad_norm": 1.09108567237854,
      "learning_rate": 5e-05,
      "loss": 177.25,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 27082752000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}