{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9955555555555555,
  "eval_steps": 500,
  "global_step": 112,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 7.216278553009033,
      "learning_rate": 8.333333333333334e-06,
      "loss": 2.4521,
      "step": 10
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 5.572214603424072,
      "learning_rate": 9.842915805643156e-06,
      "loss": 2.1638,
      "step": 20
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 2.498288631439209,
      "learning_rate": 9.221639627510076e-06,
      "loss": 1.9103,
      "step": 30
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 3.3242993354797363,
      "learning_rate": 8.18711994874345e-06,
      "loss": 1.7952,
      "step": 40
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 2.2792470455169678,
      "learning_rate": 6.840622763423391e-06,
      "loss": 1.6722,
      "step": 50
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 2.598036289215088,
      "learning_rate": 5.3139525976465675e-06,
      "loss": 1.6154,
      "step": 60
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 2.531435489654541,
      "learning_rate": 3.756550564175727e-06,
      "loss": 1.6036,
      "step": 70
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 2.560697317123413,
      "learning_rate": 2.320866025105016e-06,
      "loss": 1.5899,
      "step": 80
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.3769493103027344,
      "learning_rate": 1.1474337861210543e-06,
      "loss": 1.6193,
      "step": 90
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 2.1420528888702393,
      "learning_rate": 3.511175705587433e-07,
      "loss": 1.569,
      "step": 100
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 1.8092883825302124,
      "learning_rate": 9.866357858642206e-09,
      "loss": 1.5909,
      "step": 110
    },
    {
      "epoch": 0.9955555555555555,
      "step": 112,
      "total_flos": 1.2980476361834496e+16,
      "train_loss": 1.7745797293526786,
      "train_runtime": 341.4533,
      "train_samples_per_second": 2.636,
      "train_steps_per_second": 0.328
    }
  ],
  "logging_steps": 10,
  "max_steps": 112,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.2980476361834496e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}