trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012092661331875204,
  "global_step": 11500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 4.9991237201933425e-05,
      "loss": 3.5502,
      "step": 500
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.9982474403866854e-05,
      "loss": 3.0742,
      "step": 1000
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.997371160580027e-05,
      "loss": 2.9389,
      "step": 1500
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.99649488077337e-05,
      "loss": 2.8079,
      "step": 2000
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.995618600966712e-05,
      "loss": 2.7687,
      "step": 2500
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.9947423211600545e-05,
      "loss": 2.7448,
      "step": 3000
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.993866041353397e-05,
      "loss": 2.6388,
      "step": 3500
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.992989761546739e-05,
      "loss": 2.6045,
      "step": 4000
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.992113481740082e-05,
      "loss": 2.5276,
      "step": 4500
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.991237201933424e-05,
      "loss": 2.5322,
      "step": 5000
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9903609221267665e-05,
      "loss": 2.4583,
      "step": 5500
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.989484642320109e-05,
      "loss": 2.5075,
      "step": 6000
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.988608362513451e-05,
      "loss": 2.4178,
      "step": 6500
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.987732082706794e-05,
      "loss": 2.3881,
      "step": 7000
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.986855802900136e-05,
      "loss": 2.3897,
      "step": 7500
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.985979523093478e-05,
      "loss": 2.3356,
      "step": 8000
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.985103243286821e-05,
      "loss": 2.3406,
      "step": 8500
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.984226963480163e-05,
      "loss": 2.3413,
      "step": 9000
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.983350683673505e-05,
      "loss": 2.3287,
      "step": 9500
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9824744038668475e-05,
      "loss": 2.3343,
      "step": 10000
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.98159812406019e-05,
      "loss": 2.3305,
      "step": 10500
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.980721844253533e-05,
      "loss": 2.3109,
      "step": 11000
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.979845564446875e-05,
      "loss": 2.3059,
      "step": 11500
    }
  ],
  "max_steps": 2852970,
  "num_train_epochs": 3,
  "total_flos": 1.082983380369408e+16,
  "trial_name": null,
  "trial_params": null
}