{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0003063936699067797,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.127873398135595e-05,
      "grad_norm": 8.051688194274902,
      "learning_rate": 1e-05,
      "loss": 31.1017,
      "step": 1
    },
    {
      "epoch": 6.127873398135595e-05,
      "eval_loss": 1.9866119623184204,
      "eval_runtime": 1602.091,
      "eval_samples_per_second": 17.156,
      "eval_steps_per_second": 8.578,
      "step": 1
    },
    {
      "epoch": 0.0001225574679627119,
      "grad_norm": 8.028358459472656,
      "learning_rate": 2e-05,
      "loss": 31.4894,
      "step": 2
    },
    {
      "epoch": 0.0001225574679627119,
      "eval_loss": 1.9578453302383423,
      "eval_runtime": 1583.6409,
      "eval_samples_per_second": 17.356,
      "eval_steps_per_second": 8.678,
      "step": 2
    },
    {
      "epoch": 0.00018383620194406782,
      "grad_norm": 8.999253273010254,
      "learning_rate": 3e-05,
      "loss": 33.9703,
      "step": 3
    },
    {
      "epoch": 0.0002451149359254238,
      "grad_norm": 9.006853103637695,
      "learning_rate": 4e-05,
      "loss": 31.5724,
      "step": 4
    },
    {
      "epoch": 0.0002451149359254238,
      "eval_loss": 1.9366836547851562,
      "eval_runtime": 1569.4882,
      "eval_samples_per_second": 17.512,
      "eval_steps_per_second": 8.756,
      "step": 4
    },
    {
      "epoch": 0.0003063936699067797,
      "grad_norm": 10.690298080444336,
      "learning_rate": 5e-05,
      "loss": 33.5688,
      "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": 7203114492887040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}