{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 25000,
  "global_step": 178100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2807411566535654,
      "grad_norm": 25.670791625976562,
      "learning_rate": 4.776186911223408e-05,
      "loss": 2.2509,
      "step": 25000
    },
    {
      "epoch": 0.2807411566535654,
      "eval_loss": 1.907800555229187,
      "eval_runtime": 1183.5578,
      "eval_samples_per_second": 150.478,
      "eval_steps_per_second": 1.176,
      "step": 25000
    },
    {
      "epoch": 0.5614823133071308,
      "grad_norm": 27.820302963256836,
      "learning_rate": 3.996599912658307e-05,
      "loss": 1.9956,
      "step": 50000
    },
    {
      "epoch": 0.5614823133071308,
      "eval_loss": 1.7114382982254028,
      "eval_runtime": 1201.8966,
      "eval_samples_per_second": 148.182,
      "eval_steps_per_second": 1.158,
      "step": 50000
    },
    {
      "epoch": 0.8422234699606962,
      "grad_norm": 19.808177947998047,
      "learning_rate": 3.217106494478758e-05,
      "loss": 1.7858,
      "step": 75000
    },
    {
      "epoch": 0.8422234699606962,
      "eval_loss": 1.5567296743392944,
      "eval_runtime": 1196.901,
      "eval_samples_per_second": 148.801,
      "eval_steps_per_second": 1.163,
      "step": 75000
    },
    {
      "epoch": 1.1229646266142617,
      "grad_norm": 13.513537406921387,
      "learning_rate": 2.437550689375507e-05,
      "loss": 1.6379,
      "step": 100000
    },
    {
      "epoch": 1.1229646266142617,
      "eval_loss": 1.4506515264511108,
      "eval_runtime": 1128.3856,
      "eval_samples_per_second": 157.836,
      "eval_steps_per_second": 1.234,
      "step": 100000
    },
    {
      "epoch": 1.403705783267827,
      "grad_norm": 13.943450927734375,
      "learning_rate": 1.657932497348556e-05,
      "loss": 1.5144,
      "step": 125000
    },
    {
      "epoch": 1.403705783267827,
      "eval_loss": 1.35755455493927,
      "eval_runtime": 1141.3087,
      "eval_samples_per_second": 156.049,
      "eval_steps_per_second": 1.22,
      "step": 125000
    },
    {
      "epoch": 1.6844469399213926,
      "grad_norm": 18.438793182373047,
      "learning_rate": 8.784078857071558e-06,
      "loss": 1.411,
      "step": 150000
    },
    {
      "epoch": 1.6844469399213926,
      "eval_loss": 1.28085196018219,
      "eval_runtime": 1121.6941,
      "eval_samples_per_second": 158.778,
      "eval_steps_per_second": 1.241,
      "step": 150000
    },
    {
      "epoch": 1.9651880965749577,
      "grad_norm": 7.969166278839111,
      "learning_rate": 9.878969368020464e-07,
      "loss": 1.3335,
      "step": 175000
    },
    {
      "epoch": 1.9651880965749577,
      "eval_loss": 1.2316101789474487,
      "eval_runtime": 1133.5552,
      "eval_samples_per_second": 157.116,
      "eval_steps_per_second": 1.228,
      "step": 175000
    }
  ],
  "logging_steps": 25000,
  "max_steps": 178100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.328028350210777e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}