trainer_state.json

{
  "best_metric": 27.3,
  "best_model_checkpoint": "outputs/hf/None/2023_12_18_08_41_35/checkpoint-1428",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1428,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7,
      "learning_rate": 9.299719887955183e-06,
      "loss": 1.6858,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_bertscore_f1": 87.5,
      "eval_bertscore_precision": 87.9,
      "eval_bertscore_recall": 87.1,
      "eval_loss": 2.0261785984039307,
      "eval_rouge1": 41.1,
      "eval_rouge2": 19.3,
      "eval_rougeL": 27.1,
      "eval_rougeLsum": 37.3,
      "eval_runtime": 4513.7695,
      "eval_samples_per_second": 0.108,
      "eval_steps_per_second": 0.108,
      "step": 714
    },
    {
      "epoch": 1.4,
      "learning_rate": 8.599439775910365e-06,
      "loss": 1.1309,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_bertscore_f1": 87.4,
      "eval_bertscore_precision": 87.8,
      "eval_bertscore_recall": 87.1,
      "eval_loss": 2.088923692703247,
      "eval_rouge1": 40.8,
      "eval_rouge2": 19.6,
      "eval_rougeL": 27.3,
      "eval_rougeLsum": 37.1,
      "eval_runtime": 4300.3072,
      "eval_samples_per_second": 0.114,
      "eval_steps_per_second": 0.114,
      "step": 1428
    }
  ],
  "logging_steps": 500,
  "max_steps": 7140,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 2877934930624512.0,
  "trial_name": null,
  "trial_params": null
}