checkpoint-102/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.206060606060606,
  "eval_steps": 500,
  "global_step": 102,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 0.000132,
      "loss": 1.3647,
      "step": 33
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00019280898876404497,
      "loss": 1.2539,
      "step": 66
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00017797752808988766,
      "loss": 1.1599,
      "step": 99
    }
  ],
  "logging_steps": 33,
  "max_steps": 495,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 8467130269827072.0,
  "trial_name": null,
  "trial_params": null
}