trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.964221824686941,
  "global_step": 5550,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.45,
      "learning_rate": 4.5527728085867624e-05,
      "loss": 0.9916,
      "step": 500
    },
    {
      "epoch": 0.89,
      "learning_rate": 4.1055456171735245e-05,
      "loss": 0.8946,
      "step": 1000
    },
    {
      "epoch": 1.34,
      "learning_rate": 3.658318425760287e-05,
      "loss": 0.6054,
      "step": 1500
    },
    {
      "epoch": 1.79,
      "learning_rate": 3.211091234347048e-05,
      "loss": 0.5278,
      "step": 2000
    },
    {
      "epoch": 2.24,
      "learning_rate": 2.7638640429338103e-05,
      "loss": 0.4049,
      "step": 2500
    },
    {
      "epoch": 2.68,
      "learning_rate": 2.3166368515205725e-05,
      "loss": 0.2935,
      "step": 3000
    },
    {
      "epoch": 3.13,
      "learning_rate": 1.8694096601073346e-05,
      "loss": 0.2635,
      "step": 3500
    },
    {
      "epoch": 3.58,
      "learning_rate": 1.4221824686940966e-05,
      "loss": 0.1482,
      "step": 4000
    },
    {
      "epoch": 4.03,
      "learning_rate": 9.749552772808588e-06,
      "loss": 0.167,
      "step": 4500
    },
    {
      "epoch": 4.47,
      "learning_rate": 5.277280858676208e-06,
      "loss": 0.0716,
      "step": 5000
    },
    {
      "epoch": 4.92,
      "learning_rate": 8.050089445438284e-07,
      "loss": 0.0764,
      "step": 5500
    }
  ],
  "max_steps": 5590,
  "num_train_epochs": 5,
  "total_flos": 9126529033843200.0,
  "trial_name": null,
  "trial_params": null
}