trainer_state.json

{
  "best_metric": 30.9909,
  "best_model_checkpoint": "/content/gdrive/MyDrive/FYP/Models/t5-base-bt5/checkpoint-200",
  "epoch": 2.3255813953488373,
  "eval_steps": 200,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.47,
      "grad_norm": 0.18016715347766876,
      "learning_rate": 3.37984496124031e-05,
      "loss": 0.1634,
      "step": 200
    },
    {
      "epoch": 0.47,
      "eval_gen_len": 8.2724,
      "eval_loss": 0.14691275358200073,
      "eval_rouge1": 30.9909,
      "eval_rouge2": 15.2561,
      "eval_rougeL": 30.4111,
      "eval_rougeLsum": 30.419,
      "eval_runtime": 25.2751,
      "eval_samples_per_second": 10.168,
      "eval_steps_per_second": 1.306,
      "step": 200
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.26735684275627136,
      "learning_rate": 2.7596899224806204e-05,
      "loss": 0.1514,
      "step": 400
    },
    {
      "epoch": 0.93,
      "eval_gen_len": 8.4163,
      "eval_loss": 0.14355924725532532,
      "eval_rouge1": 30.5821,
      "eval_rouge2": 14.6428,
      "eval_rougeL": 29.9284,
      "eval_rougeLsum": 29.9879,
      "eval_runtime": 24.7715,
      "eval_samples_per_second": 10.375,
      "eval_steps_per_second": 1.332,
      "step": 400
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.24088045954704285,
      "learning_rate": 2.1395348837209303e-05,
      "loss": 0.1425,
      "step": 600
    },
    {
      "epoch": 1.4,
      "eval_gen_len": 8.4864,
      "eval_loss": 0.14273881912231445,
      "eval_rouge1": 30.8369,
      "eval_rouge2": 15.0462,
      "eval_rougeL": 30.335,
      "eval_rougeLsum": 30.3694,
      "eval_runtime": 26.6695,
      "eval_samples_per_second": 9.636,
      "eval_steps_per_second": 1.237,
      "step": 600
    },
    {
      "epoch": 1.86,
      "grad_norm": 0.23194265365600586,
      "learning_rate": 1.5193798449612405e-05,
      "loss": 0.1374,
      "step": 800
    },
    {
      "epoch": 1.86,
      "eval_gen_len": 8.4708,
      "eval_loss": 0.14196665585041046,
      "eval_rouge1": 30.6096,
      "eval_rouge2": 15.0165,
      "eval_rougeL": 30.0205,
      "eval_rougeLsum": 30.0294,
      "eval_runtime": 25.883,
      "eval_samples_per_second": 9.929,
      "eval_steps_per_second": 1.275,
      "step": 800
    },
    {
      "epoch": 2.33,
      "grad_norm": 0.5157263278961182,
      "learning_rate": 8.992248062015505e-06,
      "loss": 0.1315,
      "step": 1000
    },
    {
      "epoch": 2.33,
      "eval_gen_len": 8.4086,
      "eval_loss": 0.141823410987854,
      "eval_rouge1": 30.5898,
      "eval_rouge2": 15.182,
      "eval_rougeL": 29.9966,
      "eval_rougeLsum": 30.0044,
      "eval_runtime": 25.75,
      "eval_samples_per_second": 9.981,
      "eval_steps_per_second": 1.282,
      "step": 1000
    }
  ],
  "logging_steps": 200,
  "max_steps": 1290,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "total_flos": 4926469334630400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}