trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.527415143603133,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_gen_len": 94.0526,
      "eval_loss": 0.7492660284042358,
      "eval_rouge-1": 53.4952,
      "eval_rouge-2": 36.0108,
      "eval_rouge-l": 50.182,
      "eval_runtime": 234.7689,
      "eval_samples_per_second": 0.405,
      "eval_steps_per_second": 0.204,
      "step": 383
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.6292428198433423e-05,
      "loss": 0.678,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 84.5579,
      "eval_loss": 0.7632046341896057,
      "eval_rouge-1": 55.1066,
      "eval_rouge-2": 37.3528,
      "eval_rouge-l": 51.2075,
      "eval_runtime": 126.1849,
      "eval_samples_per_second": 0.753,
      "eval_steps_per_second": 0.38,
      "step": 766
    },
    {
      "epoch": 2.61,
      "learning_rate": 1.256247668780306e-05,
      "loss": 0.3715,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 91.2632,
      "eval_loss": 0.8486695885658264,
      "eval_rouge-1": 54.3003,
      "eval_rouge-2": 36.1799,
      "eval_rouge-l": 50.6709,
      "eval_runtime": 132.7271,
      "eval_samples_per_second": 0.716,
      "eval_steps_per_second": 0.362,
      "step": 1149
    },
    {
      "epoch": 3.92,
      "learning_rate": 8.839985080193958e-06,
      "loss": 0.217,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 89.6211,
      "eval_loss": 0.9863687753677368,
      "eval_rouge-1": 54.1436,
      "eval_rouge-2": 35.8237,
      "eval_rouge-l": 50.1118,
      "eval_runtime": 132.6394,
      "eval_samples_per_second": 0.716,
      "eval_steps_per_second": 0.362,
      "step": 1532
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 85.8947,
      "eval_loss": 1.104886770248413,
      "eval_rouge-1": 55.0895,
      "eval_rouge-2": 36.1364,
      "eval_rouge-l": 51.2227,
      "eval_runtime": 127.3071,
      "eval_samples_per_second": 0.746,
      "eval_steps_per_second": 0.377,
      "step": 1915
    },
    {
      "epoch": 5.22,
      "learning_rate": 5.110033569563596e-06,
      "loss": 0.1121,
      "step": 2000
    },
    {
      "epoch": 6.0,
      "eval_gen_len": 84.5474,
      "eval_loss": 1.2047064304351807,
      "eval_rouge-1": 54.1134,
      "eval_rouge-2": 35.4271,
      "eval_rouge-l": 50.1432,
      "eval_runtime": 128.8352,
      "eval_samples_per_second": 0.737,
      "eval_steps_per_second": 0.373,
      "step": 2298
    },
    {
      "epoch": 6.53,
      "learning_rate": 1.3800820589332339e-06,
      "loss": 0.0628,
      "step": 2500
    }
  ],
  "max_steps": 2681,
  "num_train_epochs": 7,
  "total_flos": 5084996667949056.0,
  "trial_name": null,
  "trial_params": null
}