{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.88,
  "eval_steps": 500,
  "global_step": 24,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "grad_norm": 27.128768920898438,
      "learning_rate": 0.00018333333333333334,
      "loss": 9.6266,
      "step": 2
    },
    {
      "epoch": 0.32,
      "grad_norm": 24.79010009765625,
      "learning_rate": 0.000175,
      "loss": 9.0447,
      "step": 4
    },
    {
      "epoch": 0.48,
      "grad_norm": 18.81116485595703,
      "learning_rate": 0.00015833333333333332,
      "loss": 8.5322,
      "step": 6
    },
    {
      "epoch": 0.64,
      "grad_norm": 26.39373779296875,
      "learning_rate": 0.00014166666666666668,
      "loss": 7.9093,
      "step": 8
    },
    {
      "epoch": 0.8,
      "grad_norm": 23.423715591430664,
      "learning_rate": 0.000125,
      "loss": 7.6659,
      "step": 10
    },
    {
      "epoch": 0.96,
      "grad_norm": 12.479715347290039,
      "learning_rate": 0.00010833333333333333,
      "loss": 7.5728,
      "step": 12
    },
    {
      "epoch": 1.08,
      "grad_norm": 8.727032661437988,
      "learning_rate": 9.166666666666667e-05,
      "loss": 5.5276,
      "step": 14
    },
    {
      "epoch": 1.24,
      "grad_norm": 6.857452869415283,
      "learning_rate": 7.500000000000001e-05,
      "loss": 7.3248,
      "step": 16
    },
    {
      "epoch": 1.4,
      "grad_norm": 12.307377815246582,
      "learning_rate": 5.833333333333334e-05,
      "loss": 7.1551,
      "step": 18
    },
    {
      "epoch": 1.56,
      "grad_norm": 5.698224067687988,
      "learning_rate": 4.166666666666667e-05,
      "loss": 7.0827,
      "step": 20
    },
    {
      "epoch": 1.72,
      "grad_norm": 7.9674906730651855,
      "learning_rate": 2.5e-05,
      "loss": 7.1063,
      "step": 22
    },
    {
      "epoch": 1.88,
      "grad_norm": 5.259669303894043,
      "learning_rate": 8.333333333333334e-06,
      "loss": 6.9544,
      "step": 24
    },
    {
      "epoch": 1.88,
      "step": 24,
      "total_flos": 60263854292736.0,
      "train_loss": 7.62520436445872,
      "train_runtime": 205.0269,
      "train_samples_per_second": 1.951,
      "train_steps_per_second": 0.117
    }
  ],
  "logging_steps": 2,
  "max_steps": 24,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 60263854292736.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}