trainer_state.json

{
  "best_metric": 2.888463020324707,
  "best_model_checkpoint": "output/as-i-lay-dying/checkpoint-24",
  "epoch": 3.0,
  "global_step": 24,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.62,
      "learning_rate": 4.2347916539754844e-05,
      "loss": 3.2892,
      "step": 5
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.9820306301116943,
      "eval_runtime": 0.1663,
      "eval_samples_per_second": 72.177,
      "eval_steps_per_second": 12.029,
      "step": 8
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.009247481060283e-05,
      "loss": 3.0726,
      "step": 10
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00013197813593027427,
      "loss": 3.0374,
      "step": 15
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.95857834815979,
      "eval_runtime": 0.1659,
      "eval_samples_per_second": 72.316,
      "eval_steps_per_second": 12.053,
      "step": 16
    },
    {
      "epoch": 2.5,
      "learning_rate": 6.860000000000001e-05,
      "loss": 2.8422,
      "step": 20
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.888463020324707,
      "eval_runtime": 0.1662,
      "eval_samples_per_second": 72.182,
      "eval_steps_per_second": 12.03,
      "step": 24
    }
  ],
  "max_steps": 400,
  "num_train_epochs": 50,
  "total_flos": 25084035072000.0,
  "trial_name": null,
  "trial_params": null
}