{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.020372822654578793,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004074564530915758,
      "eval_loss": 2.328631639480591,
      "eval_runtime": 72.9398,
      "eval_samples_per_second": 14.176,
      "eval_steps_per_second": 7.088,
      "step": 1
    },
    {
      "epoch": 0.0020372822654578793,
      "grad_norm": 31.550853729248047,
      "learning_rate": 5e-05,
      "loss": 8.5512,
      "step": 5
    },
    {
      "epoch": 0.0040745645309157585,
      "grad_norm": 14.368852615356445,
      "learning_rate": 0.0001,
      "loss": 6.4378,
      "step": 10
    },
    {
      "epoch": 0.0040745645309157585,
      "eval_loss": 1.3571594953536987,
      "eval_runtime": 73.9923,
      "eval_samples_per_second": 13.974,
      "eval_steps_per_second": 6.987,
      "step": 10
    },
    {
      "epoch": 0.006111846796373638,
      "grad_norm": 14.908891677856445,
      "learning_rate": 9.619397662556435e-05,
      "loss": 4.7633,
      "step": 15
    },
    {
      "epoch": 0.008149129061831517,
      "grad_norm": 12.851963996887207,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.1233,
      "step": 20
    },
    {
      "epoch": 0.008149129061831517,
      "eval_loss": 1.1030701398849487,
      "eval_runtime": 74.2697,
      "eval_samples_per_second": 13.922,
      "eval_steps_per_second": 6.961,
      "step": 20
    },
    {
      "epoch": 0.010186411327289396,
      "grad_norm": 12.32118034362793,
      "learning_rate": 6.91341716182545e-05,
      "loss": 4.402,
      "step": 25
    },
    {
      "epoch": 0.012223693592747276,
      "grad_norm": 13.023165702819824,
      "learning_rate": 5e-05,
      "loss": 4.1528,
      "step": 30
    },
    {
      "epoch": 0.012223693592747276,
      "eval_loss": 1.048792839050293,
      "eval_runtime": 74.0444,
      "eval_samples_per_second": 13.965,
      "eval_steps_per_second": 6.982,
      "step": 30
    },
    {
      "epoch": 0.014260975858205155,
      "grad_norm": 9.307778358459473,
      "learning_rate": 3.086582838174551e-05,
      "loss": 3.9542,
      "step": 35
    },
    {
      "epoch": 0.016298258123663034,
      "grad_norm": 14.647441864013672,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 4.3534,
      "step": 40
    },
    {
      "epoch": 0.016298258123663034,
      "eval_loss": 1.0314518213272095,
      "eval_runtime": 74.2852,
      "eval_samples_per_second": 13.919,
      "eval_steps_per_second": 6.96,
      "step": 40
    },
    {
      "epoch": 0.018335540389120913,
      "grad_norm": 8.370624542236328,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 3.4477,
      "step": 45
    },
    {
      "epoch": 0.020372822654578793,
      "grad_norm": 10.46690559387207,
      "learning_rate": 0.0,
      "loss": 4.6308,
      "step": 50
    },
    {
      "epoch": 0.020372822654578793,
      "eval_loss": 1.0267705917358398,
      "eval_runtime": 74.0879,
      "eval_samples_per_second": 13.956,
      "eval_steps_per_second": 6.978,
      "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": 9683500567363584.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}