last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1640,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_gen_len": 11.120274914089347,
      "eval_loss": 24.898656845092773,
      "eval_rouge1": 29.9366,
      "eval_rouge2": 22.9687,
      "eval_rougeL": 26.9975,
      "eval_rougeLsum": 27.1774,
      "eval_runtime": 152.4326,
      "eval_samples_per_second": 1.909,
      "eval_steps_per_second": 0.243,
      "step": 328
    },
    {
      "epoch": 1.52,
      "learning_rate": 2e-05,
      "loss": 25.467,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 0.0,
      "eval_loss": 1.3504424095153809,
      "eval_rouge1": 51.142,
      "eval_rouge2": 49.8705,
      "eval_rougeL": 51.1588,
      "eval_rougeLsum": 51.1528,
      "eval_runtime": 153.7577,
      "eval_samples_per_second": 1.893,
      "eval_steps_per_second": 0.241,
      "step": 656
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 14.927835051546392,
      "eval_loss": 0.8221376538276672,
      "eval_rouge1": 19.5594,
      "eval_rouge2": 12.7325,
      "eval_rougeL": 16.4586,
      "eval_rougeLsum": 16.7605,
      "eval_runtime": 157.0696,
      "eval_samples_per_second": 1.853,
      "eval_steps_per_second": 0.236,
      "step": 984
    },
    {
      "epoch": 3.05,
      "learning_rate": 1.1228070175438597e-05,
      "loss": 1.8759,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 14.109965635738831,
      "eval_loss": 0.7782504558563232,
      "eval_rouge1": 21.8348,
      "eval_rouge2": 14.9645,
      "eval_rougeL": 18.7764,
      "eval_rougeLsum": 19.0709,
      "eval_runtime": 155.486,
      "eval_samples_per_second": 1.872,
      "eval_steps_per_second": 0.238,
      "step": 1312
    },
    {
      "epoch": 4.57,
      "learning_rate": 2.456140350877193e-06,
      "loss": 0.8715,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 13.051546391752577,
      "eval_loss": 0.766891360282898,
      "eval_rouge1": 24.6538,
      "eval_rouge2": 17.821,
      "eval_rougeL": 21.5884,
      "eval_rougeLsum": 21.9045,
      "eval_runtime": 157.0206,
      "eval_samples_per_second": 1.853,
      "eval_steps_per_second": 0.236,
      "step": 1640
    }
  ],
  "logging_steps": 500,
  "max_steps": 1640,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1.229071090286592e+16,
  "trial_name": null,
  "trial_params": null
}