{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.026947368421052633,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006736842105263158,
      "grad_norm": 0.017977947369217873,
      "learning_rate": 1e-05,
      "loss": 10.3807,
      "step": 1
    },
    {
      "epoch": 0.006736842105263158,
      "eval_loss": 10.377302169799805,
      "eval_runtime": 8.3153,
      "eval_samples_per_second": 30.065,
      "eval_steps_per_second": 15.033,
      "step": 1
    },
    {
      "epoch": 0.013473684210526317,
      "grad_norm": 0.016643421724438667,
      "learning_rate": 2e-05,
      "loss": 10.3788,
      "step": 2
    },
    {
      "epoch": 0.013473684210526317,
      "eval_loss": 10.377298355102539,
      "eval_runtime": 0.6528,
      "eval_samples_per_second": 382.938,
      "eval_steps_per_second": 191.469,
      "step": 2
    },
    {
      "epoch": 0.020210526315789474,
      "grad_norm": 0.014125168323516846,
      "learning_rate": 3e-05,
      "loss": 10.3787,
      "step": 3
    },
    {
      "epoch": 0.026947368421052633,
      "grad_norm": 0.02078082039952278,
      "learning_rate": 4e-05,
      "loss": 10.3781,
      "step": 4
    },
    {
      "epoch": 0.026947368421052633,
      "eval_loss": 10.377281188964844,
      "eval_runtime": 0.6902,
      "eval_samples_per_second": 362.222,
      "eval_steps_per_second": 181.111,
      "step": 4
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 206894530560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}