{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010161956176563989,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025404890441409972,
      "grad_norm": 1.1897236108779907,
      "learning_rate": 1e-05,
      "loss": 0.6183,
      "step": 1
    },
    {
      "epoch": 0.0025404890441409972,
      "eval_loss": 0.7718630433082581,
      "eval_runtime": 179.4729,
      "eval_samples_per_second": 3.694,
      "eval_steps_per_second": 1.85,
      "step": 1
    },
    {
      "epoch": 0.0050809780882819944,
      "grad_norm": 1.1578046083450317,
      "learning_rate": 2e-05,
      "loss": 0.784,
      "step": 2
    },
    {
      "epoch": 0.0050809780882819944,
      "eval_loss": 0.7377236485481262,
      "eval_runtime": 16.4544,
      "eval_samples_per_second": 40.293,
      "eval_steps_per_second": 20.177,
      "step": 2
    },
    {
      "epoch": 0.007621467132422992,
      "grad_norm": 1.0568405389785767,
      "learning_rate": 3e-05,
      "loss": 0.5769,
      "step": 3
    },
    {
      "epoch": 0.010161956176563989,
      "grad_norm": 1.1675392389297485,
      "learning_rate": 4e-05,
      "loss": 0.8007,
      "step": 4
    },
    {
      "epoch": 0.010161956176563989,
      "eval_loss": 0.6899632215499878,
      "eval_runtime": 16.5009,
      "eval_samples_per_second": 40.18,
      "eval_steps_per_second": 20.12,
      "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": 3098020115644416.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}