trainer_state.json

{
  "best_metric": 11.0454,
  "best_model_checkpoint": "/content/gdrive/MyDrive/FYP/Models/t5-base-bt3/checkpoint-200",
  "epoch": 2.2988505747126435,
  "eval_steps": 100,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.15,
      "grad_norm": 0.2406858205795288,
      "learning_rate": 1.850574712643678e-05,
      "loss": 0.212,
      "step": 100
    },
    {
      "epoch": 1.15,
      "eval_gen_len": 9.4468,
      "eval_loss": 0.18196970224380493,
      "eval_rouge1": 9.6492,
      "eval_rouge2": 0.3273,
      "eval_rougeL": 9.4017,
      "eval_rougeLsum": 9.513,
      "eval_runtime": 7.4325,
      "eval_samples_per_second": 6.324,
      "eval_steps_per_second": 0.807,
      "step": 100
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.25088784098625183,
      "learning_rate": 7.011494252873563e-06,
      "loss": 0.1855,
      "step": 200
    },
    {
      "epoch": 2.3,
      "eval_gen_len": 8.8511,
      "eval_loss": 0.1775360256433487,
      "eval_rouge1": 11.0454,
      "eval_rouge2": 0.7529,
      "eval_rougeL": 10.8168,
      "eval_rougeLsum": 10.8709,
      "eval_runtime": 5.0258,
      "eval_samples_per_second": 9.352,
      "eval_steps_per_second": 1.194,
      "step": 200
    }
  ],
  "logging_steps": 100,
  "max_steps": 261,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 971896793333760.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}