{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.019451468585878234,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00038902937171756465,
      "eval_loss": 2.161581039428711,
      "eval_runtime": 231.553,
      "eval_samples_per_second": 4.677,
      "eval_steps_per_second": 2.341,
      "step": 1
    },
    {
      "epoch": 0.0019451468585878235,
      "grad_norm": 0.3031664490699768,
      "learning_rate": 5e-05,
      "loss": 2.1486,
      "step": 5
    },
    {
      "epoch": 0.003890293717175647,
      "grad_norm": 0.3501927852630615,
      "learning_rate": 0.0001,
      "loss": 2.1731,
      "step": 10
    },
    {
      "epoch": 0.003890293717175647,
      "eval_loss": 2.1431446075439453,
      "eval_runtime": 230.9198,
      "eval_samples_per_second": 4.69,
      "eval_steps_per_second": 2.347,
      "step": 10
    },
    {
      "epoch": 0.00583544057576347,
      "grad_norm": 0.36051422357559204,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.1834,
      "step": 15
    },
    {
      "epoch": 0.007780587434351294,
      "grad_norm": 0.4108206033706665,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.0486,
      "step": 20
    },
    {
      "epoch": 0.007780587434351294,
      "eval_loss": 2.1004695892333984,
      "eval_runtime": 47.1992,
      "eval_samples_per_second": 22.945,
      "eval_steps_per_second": 11.483,
      "step": 20
    },
    {
      "epoch": 0.009725734292939117,
      "grad_norm": 0.4609528183937073,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.1037,
      "step": 25
    },
    {
      "epoch": 0.01167088115152694,
      "grad_norm": 0.46644195914268494,
      "learning_rate": 5e-05,
      "loss": 2.094,
      "step": 30
    },
    {
      "epoch": 0.01167088115152694,
      "eval_loss": 2.082268476486206,
      "eval_runtime": 85.8113,
      "eval_samples_per_second": 12.621,
      "eval_steps_per_second": 6.316,
      "step": 30
    },
    {
      "epoch": 0.013616028010114764,
      "grad_norm": 0.45734280347824097,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.0909,
      "step": 35
    },
    {
      "epoch": 0.015561174868702588,
      "grad_norm": 0.424358606338501,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.1651,
      "step": 40
    },
    {
      "epoch": 0.015561174868702588,
      "eval_loss": 2.0750739574432373,
      "eval_runtime": 113.0128,
      "eval_samples_per_second": 9.583,
      "eval_steps_per_second": 4.796,
      "step": 40
    },
    {
      "epoch": 0.01750632172729041,
      "grad_norm": 0.486756831407547,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.107,
      "step": 45
    },
    {
      "epoch": 0.019451468585878234,
      "grad_norm": 0.4951198697090149,
      "learning_rate": 0.0,
      "loss": 2.0594,
      "step": 50
    },
    {
      "epoch": 0.019451468585878234,
      "eval_loss": 2.0739192962646484,
      "eval_runtime": 104.7943,
      "eval_samples_per_second": 10.335,
      "eval_steps_per_second": 5.172,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3242982585139200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}