{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0010232141715162755,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002046428343032551,
      "grad_norm": 0.013246643356978893,
      "learning_rate": 1e-05,
      "loss": 11.9339,
      "step": 1
    },
    {
      "epoch": 0.0002046428343032551,
      "eval_loss": 11.931361198425293,
      "eval_runtime": 26.0837,
      "eval_samples_per_second": 315.523,
      "eval_steps_per_second": 157.762,
      "step": 1
    },
    {
      "epoch": 0.0004092856686065102,
      "grad_norm": 0.011360646225512028,
      "learning_rate": 2e-05,
      "loss": 11.9346,
      "step": 2
    },
    {
      "epoch": 0.0004092856686065102,
      "eval_loss": 11.93135929107666,
      "eval_runtime": 15.7505,
      "eval_samples_per_second": 522.524,
      "eval_steps_per_second": 261.262,
      "step": 2
    },
    {
      "epoch": 0.0006139285029097653,
      "grad_norm": 0.012533008120954037,
      "learning_rate": 3e-05,
      "loss": 11.932,
      "step": 3
    },
    {
      "epoch": 0.0008185713372130205,
      "grad_norm": 0.013612398877739906,
      "learning_rate": 4e-05,
      "loss": 11.933,
      "step": 4
    },
    {
      "epoch": 0.0008185713372130205,
      "eval_loss": 11.931349754333496,
      "eval_runtime": 15.9348,
      "eval_samples_per_second": 516.479,
      "eval_steps_per_second": 258.24,
      "step": 4
    },
    {
      "epoch": 0.0010232141715162755,
      "grad_norm": 0.01218799501657486,
      "learning_rate": 5e-05,
      "loss": 11.9307,
      "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": 3426680832.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}