trainer_state.json

{
  "best_metric": 0.013348984052090439,
  "best_model_checkpoint": "./novelImgcaption/checkpoint-500",
  "epoch": 0.024948854847562495,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 4.9875505214310666e-05,
      "loss": 1.5851,
      "step": 500
    },
    {
      "epoch": 0.01,
      "eval_bleu4": 0.013348984052090439,
      "eval_loss": 1.4344794750213623,
      "eval_runtime": 166299.0493,
      "eval_samples_per_second": 0.107,
      "eval_steps_per_second": 0.027,
      "step": 500
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.975076094007286e-05,
      "loss": 1.4209,
      "step": 1000
    },
    {
      "epoch": 0.02,
      "eval_bleu4": 0.012171030703652613,
      "eval_loss": 1.3528523445129395,
      "eval_runtime": 168925.5463,
      "eval_samples_per_second": 0.105,
      "eval_steps_per_second": 0.026,
      "step": 1000
    }
  ],
  "max_steps": 200410,
  "num_train_epochs": 5,
  "total_flos": 7.21855564480512e+17,
  "trial_name": null,
  "trial_params": null
}