trainer_state.json

{
  "best_metric": 24.1034,
  "best_model_checkpoint": "/content/gdrive/MyDrive/FYP/Models/t5-base-bt1/checkpoint-200",
  "epoch": 2.5974025974025974,
  "eval_steps": 200,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.52,
      "grad_norm": 0.2686031758785248,
      "learning_rate": 2.4831168831168833e-05,
      "loss": 0.1851,
      "step": 200
    },
    {
      "epoch": 0.52,
      "eval_gen_len": 7.9725,
      "eval_loss": 0.1528128981590271,
      "eval_rouge1": 24.1034,
      "eval_rouge2": 7.8017,
      "eval_rougeL": 23.9819,
      "eval_rougeLsum": 23.9829,
      "eval_runtime": 28.1898,
      "eval_samples_per_second": 9.046,
      "eval_steps_per_second": 1.135,
      "step": 200
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.25006070733070374,
      "learning_rate": 1.963636363636364e-05,
      "loss": 0.1689,
      "step": 400
    },
    {
      "epoch": 1.04,
      "eval_gen_len": 7.7647,
      "eval_loss": 0.14707043766975403,
      "eval_rouge1": 23.678,
      "eval_rouge2": 8.9843,
      "eval_rougeL": 23.5524,
      "eval_rougeLsum": 23.4759,
      "eval_runtime": 24.6429,
      "eval_samples_per_second": 10.348,
      "eval_steps_per_second": 1.299,
      "step": 400
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.22689774632453918,
      "learning_rate": 1.444155844155844e-05,
      "loss": 0.1552,
      "step": 600
    },
    {
      "epoch": 1.56,
      "eval_gen_len": 7.7529,
      "eval_loss": 0.14518693089485168,
      "eval_rouge1": 22.9341,
      "eval_rouge2": 8.1229,
      "eval_rougeL": 22.7212,
      "eval_rougeLsum": 22.683,
      "eval_runtime": 24.959,
      "eval_samples_per_second": 10.217,
      "eval_steps_per_second": 1.282,
      "step": 600
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.17184163630008698,
      "learning_rate": 9.246753246753248e-06,
      "loss": 0.1514,
      "step": 800
    },
    {
      "epoch": 2.08,
      "eval_gen_len": 7.7608,
      "eval_loss": 0.14357559382915497,
      "eval_rouge1": 22.5133,
      "eval_rouge2": 7.2709,
      "eval_rougeL": 22.2378,
      "eval_rougeLsum": 22.2376,
      "eval_runtime": 24.8757,
      "eval_samples_per_second": 10.251,
      "eval_steps_per_second": 1.286,
      "step": 800
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.28168073296546936,
      "learning_rate": 4.051948051948052e-06,
      "loss": 0.1471,
      "step": 1000
    },
    {
      "epoch": 2.6,
      "eval_gen_len": 7.549,
      "eval_loss": 0.14313405752182007,
      "eval_rouge1": 22.1429,
      "eval_rouge2": 7.3658,
      "eval_rougeL": 21.9525,
      "eval_rougeLsum": 21.8681,
      "eval_runtime": 24.8114,
      "eval_samples_per_second": 10.278,
      "eval_steps_per_second": 1.29,
      "step": 1000
    }
  ],
  "logging_steps": 200,
  "max_steps": 1155,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "total_flos": 4869227292917760.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}