trainer_state.json

{
  "best_metric": 23.8081,
  "best_model_checkpoint": "/content/gdrive/MyDrive/FYP/Models/t5-base-bt2/checkpoint-400",
  "epoch": 2.840909090909091,
  "eval_steps": 100,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.57,
      "grad_norm": 0.2713575065135956,
      "learning_rate": 2.4318181818181818e-05,
      "loss": 0.1676,
      "step": 100
    },
    {
      "epoch": 0.57,
      "eval_gen_len": 7.3308,
      "eval_loss": 0.15983037650585175,
      "eval_rouge1": 21.6708,
      "eval_rouge2": 9.2098,
      "eval_rougeL": 21.4437,
      "eval_rougeLsum": 21.3546,
      "eval_runtime": 16.7342,
      "eval_samples_per_second": 7.948,
      "eval_steps_per_second": 1.016,
      "step": 100
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.2671663463115692,
      "learning_rate": 1.8636363636363638e-05,
      "loss": 0.1527,
      "step": 200
    },
    {
      "epoch": 1.14,
      "eval_gen_len": 7.4436,
      "eval_loss": 0.15573656558990479,
      "eval_rouge1": 22.0171,
      "eval_rouge2": 9.3228,
      "eval_rougeL": 21.6387,
      "eval_rougeLsum": 21.5998,
      "eval_runtime": 13.5793,
      "eval_samples_per_second": 9.794,
      "eval_steps_per_second": 1.252,
      "step": 200
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.310281366109848,
      "learning_rate": 1.2954545454545455e-05,
      "loss": 0.1435,
      "step": 300
    },
    {
      "epoch": 1.7,
      "eval_gen_len": 7.6165,
      "eval_loss": 0.153303861618042,
      "eval_rouge1": 22.5122,
      "eval_rouge2": 10.4875,
      "eval_rougeL": 21.8915,
      "eval_rougeLsum": 22.0003,
      "eval_runtime": 14.3705,
      "eval_samples_per_second": 9.255,
      "eval_steps_per_second": 1.183,
      "step": 300
    },
    {
      "epoch": 2.27,
      "grad_norm": 0.22745513916015625,
      "learning_rate": 7.329545454545455e-06,
      "loss": 0.1418,
      "step": 400
    },
    {
      "epoch": 2.27,
      "eval_gen_len": 7.7744,
      "eval_loss": 0.1518535614013672,
      "eval_rouge1": 23.8081,
      "eval_rouge2": 11.223,
      "eval_rougeL": 23.3821,
      "eval_rougeLsum": 23.6075,
      "eval_runtime": 14.0505,
      "eval_samples_per_second": 9.466,
      "eval_steps_per_second": 1.21,
      "step": 400
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.27223658561706543,
      "learning_rate": 1.6477272727272728e-06,
      "loss": 0.1369,
      "step": 500
    },
    {
      "epoch": 2.84,
      "eval_gen_len": 7.4812,
      "eval_loss": 0.1519903540611267,
      "eval_rouge1": 22.6861,
      "eval_rouge2": 10.8165,
      "eval_rougeL": 22.0984,
      "eval_rougeLsum": 22.2851,
      "eval_runtime": 14.0722,
      "eval_samples_per_second": 9.451,
      "eval_steps_per_second": 1.208,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 528,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 2434613646458880.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}