trainer_state.json

{
  "best_metric": 2.5199410915374756,
  "best_model_checkpoint": "flan-t5-base-samsum-Amalq/shared_TaskA/checkpoint-453",
  "epoch": 3.0,
  "global_step": 453,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_gen_len": 18.97,
      "eval_loss": 2.5625901222229004,
      "eval_rouge1": 28.4776,
      "eval_rouge2": 14.7774,
      "eval_rougeL": 28.0326,
      "eval_rougeLsum": 28.0975,
      "eval_runtime": 63.2726,
      "eval_samples_per_second": 1.58,
      "eval_steps_per_second": 0.205,
      "step": 151
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 18.88,
      "eval_loss": 2.539769172668457,
      "eval_rouge1": 27.1318,
      "eval_rouge2": 13.7771,
      "eval_rougeL": 26.658,
      "eval_rougeLsum": 26.7023,
      "eval_runtime": 63.4889,
      "eval_samples_per_second": 1.575,
      "eval_steps_per_second": 0.205,
      "step": 302
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 18.8,
      "eval_loss": 2.5199410915374756,
      "eval_rouge1": 28.3352,
      "eval_rouge2": 14.5989,
      "eval_rougeL": 27.719,
      "eval_rougeLsum": 27.8475,
      "eval_runtime": 64.2752,
      "eval_samples_per_second": 1.556,
      "eval_steps_per_second": 0.202,
      "step": 453
    }
  ],
  "max_steps": 755,
  "num_train_epochs": 5,
  "total_flos": 2467180740870144.0,
  "trial_name": null,
  "trial_params": null
}