{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9991993594875901,
  "eval_steps": 4,
  "global_step": 78,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.051240992794235385,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.8604,
      "step": 4
    },
    {
      "epoch": 0.10248198558847077,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.9174,
      "step": 8
    },
    {
      "epoch": 0.15372297838270615,
      "grad_norm": 0.22256438434123993,
      "learning_rate": 0.002,
      "loss": 0.9102,
      "step": 12
    },
    {
      "epoch": 0.20496397117694154,
      "grad_norm": 0.14360007643699646,
      "learning_rate": 0.0011547005383792518,
      "loss": 0.8065,
      "step": 16
    },
    {
      "epoch": 0.2562049639711769,
      "grad_norm": 0.269815057516098,
      "learning_rate": 0.0007559289460184544,
      "loss": 0.7581,
      "step": 20
    },
    {
      "epoch": 0.3074459567654123,
      "grad_norm": 0.1919809728860855,
      "learning_rate": 0.0006030226891555273,
      "loss": 0.6564,
      "step": 24
    },
    {
      "epoch": 0.3586869495596477,
      "grad_norm": 0.20717447996139526,
      "learning_rate": 0.0005345224838248488,
      "loss": 0.6483,
      "step": 28
    },
    {
      "epoch": 0.4099279423538831,
      "grad_norm": 0.16305077075958252,
      "learning_rate": 0.00047140452079103175,
      "loss": 0.6444,
      "step": 32
    },
    {
      "epoch": 0.4611689351481185,
      "grad_norm": 0.1585964411497116,
      "learning_rate": 0.00042640143271122083,
      "loss": 0.616,
      "step": 36
    },
    {
      "epoch": 0.5124099279423538,
      "grad_norm": 0.16819557547569275,
      "learning_rate": 0.0003922322702763681,
      "loss": 0.6418,
      "step": 40
    },
    {
      "epoch": 0.5636509207365893,
      "grad_norm": 0.15789124369621277,
      "learning_rate": 0.00036514837167011074,
      "loss": 0.6313,
      "step": 44
    },
    {
      "epoch": 0.6148919135308246,
      "grad_norm": 0.14483995735645294,
      "learning_rate": 0.00034299717028501764,
      "loss": 0.6054,
      "step": 48
    },
    {
      "epoch": 0.6661329063250601,
      "grad_norm": 0.17608477175235748,
      "learning_rate": 0.0003287979746107146,
      "loss": 0.6128,
      "step": 52
    },
    {
      "epoch": 0.7173738991192954,
      "grad_norm": 0.18501809239387512,
      "learning_rate": 0.0003123475237772121,
      "loss": 0.6161,
      "step": 56
    },
    {
      "epoch": 0.7686148919135308,
      "grad_norm": 0.1523313969373703,
      "learning_rate": 0.00029814239699997195,
      "loss": 0.6128,
      "step": 60
    },
    {
      "epoch": 0.8198558847077662,
      "grad_norm": 0.1530931144952774,
      "learning_rate": 0.0002857142857142857,
      "loss": 0.5906,
      "step": 64
    },
    {
      "epoch": 0.8710968775020016,
      "grad_norm": 0.16880746185779572,
      "learning_rate": 0.0002747211278973781,
      "loss": 0.6106,
      "step": 68
    },
    {
      "epoch": 0.922337870296237,
      "grad_norm": 0.15904685854911804,
      "learning_rate": 0.00026490647141300875,
      "loss": 0.6297,
      "step": 72
    },
    {
      "epoch": 0.9735788630904724,
      "grad_norm": 0.14567361772060394,
      "learning_rate": 0.000256073759865792,
      "loss": 0.6091,
      "step": 76
    },
    {
      "epoch": 0.9991993594875901,
      "step": 78,
      "total_flos": 7.922041751265608e+17,
      "train_loss": 0.680653405495179,
      "train_runtime": 774.7537,
      "train_samples_per_second": 12.892,
      "train_steps_per_second": 0.101
    }
  ],
  "logging_steps": 4,
  "max_steps": 78,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 4,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.922041751265608e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}