trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.933780385582565,
  "global_step": 7000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21,
      "learning_rate": 4.65074043028779e-05,
      "loss": 0.0717,
      "step": 500
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.3014808605755804e-05,
      "loss": 0.0,
      "step": 1000
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.95222129086337e-05,
      "loss": 0.0,
      "step": 1500
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.60296172115116e-05,
      "loss": 0.0,
      "step": 2000
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.2537021514389497e-05,
      "loss": 0.0,
      "step": 2500
    },
    {
      "epoch": 1.26,
      "learning_rate": 2.9044425817267394e-05,
      "loss": 0.0,
      "step": 3000
    },
    {
      "epoch": 1.47,
      "learning_rate": 2.555183012014529e-05,
      "loss": 0.0,
      "step": 3500
    },
    {
      "epoch": 1.68,
      "learning_rate": 2.2059234423023192e-05,
      "loss": 0.0,
      "step": 4000
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.856663872590109e-05,
      "loss": 0.0,
      "step": 4500
    },
    {
      "epoch": 2.1,
      "learning_rate": 1.5074043028778989e-05,
      "loss": 0.0,
      "step": 5000
    },
    {
      "epoch": 2.31,
      "learning_rate": 1.1581447331656888e-05,
      "loss": 0.0,
      "step": 5500
    },
    {
      "epoch": 2.51,
      "learning_rate": 8.088851634534787e-06,
      "loss": 0.0,
      "step": 6000
    },
    {
      "epoch": 2.72,
      "learning_rate": 4.596255937412685e-06,
      "loss": 0.0,
      "step": 6500
    },
    {
      "epoch": 2.93,
      "learning_rate": 1.103660240290584e-06,
      "loss": 0.0,
      "step": 7000
    }
  ],
  "max_steps": 7158,
  "num_train_epochs": 3,
  "total_flos": 1.473369287804928e+16,
  "trial_name": null,
  "trial_params": null
}