{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001717438440565896,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003434876881131792,
      "grad_norm": 26.44883918762207,
      "learning_rate": 1e-05,
      "loss": 48.3717,
      "step": 1
    },
    {
      "epoch": 0.0003434876881131792,
      "eval_loss": 3.852907180786133,
      "eval_runtime": 208.2997,
      "eval_samples_per_second": 23.543,
      "eval_steps_per_second": 11.772,
      "step": 1
    },
    {
      "epoch": 0.0006869753762263584,
      "grad_norm": 33.235595703125,
      "learning_rate": 2e-05,
      "loss": 60.1536,
      "step": 2
    },
    {
      "epoch": 0.0006869753762263584,
      "eval_loss": 3.804044008255005,
      "eval_runtime": 274.08,
      "eval_samples_per_second": 17.893,
      "eval_steps_per_second": 8.946,
      "step": 2
    },
    {
      "epoch": 0.0010304630643395375,
      "grad_norm": 37.13601303100586,
      "learning_rate": 3e-05,
      "loss": 60.5261,
      "step": 3
    },
    {
      "epoch": 0.0013739507524527168,
      "grad_norm": 29.16879653930664,
      "learning_rate": 4e-05,
      "loss": 60.3236,
      "step": 4
    },
    {
      "epoch": 0.0013739507524527168,
      "eval_loss": 3.7563986778259277,
      "eval_runtime": 535.9462,
      "eval_samples_per_second": 9.15,
      "eval_steps_per_second": 4.575,
      "step": 4
    },
    {
      "epoch": 0.001717438440565896,
      "grad_norm": 33.736846923828125,
      "learning_rate": 5e-05,
      "loss": 53.7521,
      "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": 3461057913815040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}