{
  "best_metric": 1.285884141921997,
  "best_model_checkpoint": "monot5-base-msmarco-finetuned-monoQA-rep-HDN-CONVDR-Question-Answering-100sample/checkpoint-3941",
  "epoch": 9.0,
  "global_step": 35469,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 1.8e-05,
      "loss": 0.2134,
      "step": 3941
    },
    {
      "epoch": 1.0,
      "eval_Rel Acc": 65.42,
      "eval_loss": 1.285884141921997,
      "eval_rouge1": 10.8,
      "eval_rouge2": 6.16,
      "eval_rougeL": 9.97,
      "eval_rougeLsum": 10.02,
      "eval_runtime": 586.4065,
      "eval_samples_per_second": 4.823,
      "eval_steps_per_second": 0.302,
      "step": 3941
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.051,
      "step": 7882
    },
    {
      "epoch": 2.0,
      "eval_Rel Acc": 43.53,
      "eval_loss": 1.3421778678894043,
      "eval_rouge1": 10.09,
      "eval_rouge2": 6.8,
      "eval_rougeL": 9.49,
      "eval_rougeLsum": 9.5,
      "eval_runtime": 584.9981,
      "eval_samples_per_second": 4.834,
      "eval_steps_per_second": 0.303,
      "step": 7882
    },
    {
      "epoch": 3.0,
      "learning_rate": 1.4e-05,
      "loss": 0.0461,
      "step": 11823
    },
    {
      "epoch": 3.0,
      "eval_Rel Acc": 34.94,
      "eval_loss": 1.4272361993789673,
      "eval_rouge1": 8.96,
      "eval_rouge2": 6.5,
      "eval_rougeL": 8.56,
      "eval_rougeLsum": 8.56,
      "eval_runtime": 577.0374,
      "eval_samples_per_second": 4.901,
      "eval_steps_per_second": 0.307,
      "step": 11823
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.2e-05,
      "loss": 0.0425,
      "step": 15764
    },
    {
      "epoch": 4.0,
      "eval_Rel Acc": 34.69,
      "eval_loss": 1.5165988206863403,
      "eval_rouge1": 9.76,
      "eval_rouge2": 7.04,
      "eval_rougeL": 9.31,
      "eval_rougeLsum": 9.31,
      "eval_runtime": 70.6183,
      "eval_samples_per_second": 40.046,
      "eval_steps_per_second": 2.506,
      "step": 15764
    },
    {
      "epoch": 5.0,
      "learning_rate": 1e-05,
      "loss": 0.0401,
      "step": 19705
    },
    {
      "epoch": 5.0,
      "eval_Rel Acc": 33.7,
      "eval_loss": 1.5656001567840576,
      "eval_rouge1": 9.42,
      "eval_rouge2": 7.06,
      "eval_rougeL": 9.03,
      "eval_rougeLsum": 9.04,
      "eval_runtime": 70.3483,
      "eval_samples_per_second": 40.2,
      "eval_steps_per_second": 2.516,
      "step": 19705
    },
    {
      "epoch": 6.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.038,
      "step": 23646
    },
    {
      "epoch": 6.0,
      "eval_Rel Acc": 33.84,
      "eval_loss": 1.5563075542449951,
      "eval_rouge1": 9.21,
      "eval_rouge2": 6.96,
      "eval_rougeL": 8.83,
      "eval_rougeLsum": 8.82,
      "eval_runtime": 70.1794,
      "eval_samples_per_second": 40.297,
      "eval_steps_per_second": 2.522,
      "step": 23646
    },
    {
      "epoch": 7.0,
      "learning_rate": 6e-06,
      "loss": 0.0364,
      "step": 27587
    },
    {
      "epoch": 7.0,
      "eval_Rel Acc": 31.58,
      "eval_loss": 1.6121798753738403,
      "eval_rouge1": 9.42,
      "eval_rouge2": 7.19,
      "eval_rougeL": 9.06,
      "eval_rougeLsum": 9.07,
      "eval_runtime": 70.6676,
      "eval_samples_per_second": 40.018,
      "eval_steps_per_second": 2.505,
      "step": 27587
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0353,
      "step": 31528
    },
    {
      "epoch": 8.0,
      "eval_Rel Acc": 32.32,
      "eval_loss": 1.6281025409698486,
      "eval_rouge1": 9.84,
      "eval_rouge2": 7.47,
      "eval_rougeL": 9.46,
      "eval_rougeLsum": 9.43,
      "eval_runtime": 70.4202,
      "eval_samples_per_second": 40.159,
      "eval_steps_per_second": 2.513,
      "step": 31528
    },
    {
      "epoch": 9.0,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0342,
      "step": 35469
    },
    {
      "epoch": 9.0,
      "eval_Rel Acc": 32.07,
      "eval_loss": 1.6341171264648438,
      "eval_rouge1": 9.77,
      "eval_rouge2": 7.43,
      "eval_rougeL": 9.42,
      "eval_rougeLsum": 9.4,
      "eval_runtime": 70.4771,
      "eval_samples_per_second": 40.127,
      "eval_steps_per_second": 2.511,
      "step": 35469
    }
  ],
  "max_steps": 39410,
  "num_train_epochs": 10,
  "total_flos": 3.455584072600781e+17,
  "trial_name": null,
  "trial_params": null
}