{
  "best_metric": 29.4578,
  "best_model_checkpoint": "/content/gdrive/MyDrive/FYP/t5-base-squad/checkpoint-4000",
  "epoch": 0.91324200913242,
  "eval_steps": 1000,
  "global_step": 9000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "grad_norm": 0.5294313430786133,
      "learning_rate": 3.5961440892947744e-05,
      "loss": 0.4964,
      "step": 1000
    },
    {
      "epoch": 0.1,
      "eval_gen_len": 14.3475,
      "eval_loss": 0.20427940785884857,
      "eval_rouge1": 28.3615,
      "eval_rouge2": 8.4682,
      "eval_rougeL": 25.4968,
      "eval_rougeLsum": 25.5017,
      "eval_runtime": 1076.2576,
      "eval_samples_per_second": 8.139,
      "eval_steps_per_second": 1.017,
      "step": 1000
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.3378017246723175,
      "learning_rate": 3.19066463723998e-05,
      "loss": 0.2181,
      "step": 2000
    },
    {
      "epoch": 0.2,
      "eval_gen_len": 14.0145,
      "eval_loss": 0.19709938764572144,
      "eval_rouge1": 28.848,
      "eval_rouge2": 8.9434,
      "eval_rougeL": 25.9934,
      "eval_rougeLsum": 25.9925,
      "eval_runtime": 1064.9247,
      "eval_samples_per_second": 8.226,
      "eval_steps_per_second": 1.028,
      "step": 2000
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.4546686112880707,
      "learning_rate": 2.786808726534754e-05,
      "loss": 0.2113,
      "step": 3000
    },
    {
      "epoch": 0.3,
      "eval_gen_len": 13.3511,
      "eval_loss": 0.19329853355884552,
      "eval_rouge1": 29.2691,
      "eval_rouge2": 9.1353,
      "eval_rougeL": 26.4378,
      "eval_rougeLsum": 26.4387,
      "eval_runtime": 1053.7948,
      "eval_samples_per_second": 8.313,
      "eval_steps_per_second": 1.039,
      "step": 3000
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.3615570664405823,
      "learning_rate": 2.3829528158295285e-05,
      "loss": 0.2055,
      "step": 4000
    },
    {
      "epoch": 0.41,
      "eval_gen_len": 14.0945,
      "eval_loss": 0.1883835792541504,
      "eval_rouge1": 29.4578,
      "eval_rouge2": 9.2642,
      "eval_rougeL": 26.5988,
      "eval_rougeLsum": 26.6249,
      "eval_runtime": 1085.8301,
      "eval_samples_per_second": 8.068,
      "eval_steps_per_second": 1.008,
      "step": 4000
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.3282989263534546,
      "learning_rate": 1.9795027904616947e-05,
      "loss": 0.2032,
      "step": 5000
    },
    {
      "epoch": 0.51,
      "eval_gen_len": 14.0758,
      "eval_loss": 0.18715335428714752,
      "eval_rouge1": 29.1722,
      "eval_rouge2": 9.0803,
      "eval_rougeL": 26.3435,
      "eval_rougeLsum": 26.3577,
      "eval_runtime": 1079.1365,
      "eval_samples_per_second": 8.118,
      "eval_steps_per_second": 1.015,
      "step": 5000
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.43038222193717957,
      "learning_rate": 1.5752409944190767e-05,
      "loss": 0.1997,
      "step": 6000
    },
    {
      "epoch": 0.61,
      "eval_gen_len": 14.4075,
      "eval_loss": 0.18170754611492157,
      "eval_rouge1": 29.2152,
      "eval_rouge2": 9.0871,
      "eval_rougeL": 26.2656,
      "eval_rougeLsum": 26.2699,
      "eval_runtime": 1047.9477,
      "eval_samples_per_second": 8.359,
      "eval_steps_per_second": 1.045,
      "step": 6000
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.35650455951690674,
      "learning_rate": 1.171385083713851e-05,
      "loss": 0.201,
      "step": 7000
    },
    {
      "epoch": 0.71,
      "eval_gen_len": 14.4231,
      "eval_loss": 0.18083173036575317,
      "eval_rouge1": 28.9127,
      "eval_rouge2": 8.9743,
      "eval_rougeL": 26.0338,
      "eval_rougeLsum": 26.0194,
      "eval_runtime": 1047.0949,
      "eval_samples_per_second": 8.366,
      "eval_steps_per_second": 1.046,
      "step": 7000
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.4643958508968353,
      "learning_rate": 7.675291730086252e-06,
      "loss": 0.1971,
      "step": 8000
    },
    {
      "epoch": 0.81,
      "eval_gen_len": 14.3037,
      "eval_loss": 0.18144848942756653,
      "eval_rouge1": 29.4071,
      "eval_rouge2": 9.4867,
      "eval_rougeL": 26.4771,
      "eval_rougeLsum": 26.473,
      "eval_runtime": 1059.6714,
      "eval_samples_per_second": 8.267,
      "eval_steps_per_second": 1.033,
      "step": 8000
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.4707474410533905,
      "learning_rate": 3.640791476407915e-06,
      "loss": 0.1994,
      "step": 9000
    },
    {
      "epoch": 0.91,
      "eval_gen_len": 14.1849,
      "eval_loss": 0.18111075460910797,
      "eval_rouge1": 29.293,
      "eval_rouge2": 9.3682,
      "eval_rougeL": 26.3751,
      "eval_rougeLsum": 26.3635,
      "eval_runtime": 1052.0617,
      "eval_samples_per_second": 8.327,
      "eval_steps_per_second": 1.041,
      "step": 9000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 9855,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "total_flos": 4.389855641468928e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}