{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.99744,
  "eval_steps": 500,
  "global_step": 6248,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.64,
      "learning_rate": 1.8399487836107557e-05,
      "loss": 2.1501,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.9072,
      "eval_gen_len": 25.465454545454545,
      "eval_loss": 1.7061578035354614,
      "eval_precision": 0.9082,
      "eval_recall": 0.9065,
      "eval_rouge1": 0.4566,
      "eval_rouge2": 0.209,
      "eval_rougeL": 0.3745,
      "eval_rougeLsum": 0.3744,
      "eval_runtime": 882.5908,
      "eval_samples_per_second": 6.232,
      "eval_steps_per_second": 0.39,
      "step": 781
    },
    {
      "epoch": 1.28,
      "learning_rate": 1.679897567221511e-05,
      "loss": 1.839,
      "step": 1000
    },
    {
      "epoch": 1.92,
      "learning_rate": 1.5198463508322665e-05,
      "loss": 1.7722,
      "step": 1500
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.9097,
      "eval_gen_len": 25.42981818181818,
      "eval_loss": 1.6313680410385132,
      "eval_precision": 0.9107,
      "eval_recall": 0.909,
      "eval_rouge1": 0.4712,
      "eval_rouge2": 0.2226,
      "eval_rougeL": 0.3906,
      "eval_rougeLsum": 0.3904,
      "eval_runtime": 869.6253,
      "eval_samples_per_second": 6.325,
      "eval_steps_per_second": 0.396,
      "step": 1562
    },
    {
      "epoch": 2.56,
      "learning_rate": 1.3597951344430219e-05,
      "loss": 1.7218,
      "step": 2000
    },
    {
      "epoch": 3.0,
      "eval_f1": 0.9106,
      "eval_gen_len": 25.656909090909092,
      "eval_loss": 1.594840168952942,
      "eval_precision": 0.9112,
      "eval_recall": 0.9103,
      "eval_rouge1": 0.4776,
      "eval_rouge2": 0.2284,
      "eval_rougeL": 0.3965,
      "eval_rougeLsum": 0.3963,
      "eval_runtime": 866.3975,
      "eval_samples_per_second": 6.348,
      "eval_steps_per_second": 0.397,
      "step": 2343
    },
    {
      "epoch": 3.2,
      "learning_rate": 1.1997439180537773e-05,
      "loss": 1.6923,
      "step": 2500
    },
    {
      "epoch": 3.84,
      "learning_rate": 1.0396927016645328e-05,
      "loss": 1.6668,
      "step": 3000
    },
    {
      "epoch": 4.0,
      "eval_f1": 0.9112,
      "eval_gen_len": 25.34509090909091,
      "eval_loss": 1.5707985162734985,
      "eval_precision": 0.9122,
      "eval_recall": 0.9107,
      "eval_rouge1": 0.481,
      "eval_rouge2": 0.2316,
      "eval_rougeL": 0.4002,
      "eval_rougeLsum": 0.4,
      "eval_runtime": 864.0634,
      "eval_samples_per_second": 6.365,
      "eval_steps_per_second": 0.398,
      "step": 3125
    },
    {
      "epoch": 4.48,
      "learning_rate": 8.796414852752882e-06,
      "loss": 1.6437,
      "step": 3500
    },
    {
      "epoch": 5.0,
      "eval_f1": 0.9118,
      "eval_gen_len": 25.482,
      "eval_loss": 1.5564521551132202,
      "eval_precision": 0.9127,
      "eval_recall": 0.9113,
      "eval_rouge1": 0.4844,
      "eval_rouge2": 0.2346,
      "eval_rougeL": 0.4034,
      "eval_rougeLsum": 0.4031,
      "eval_runtime": 868.5536,
      "eval_samples_per_second": 6.332,
      "eval_steps_per_second": 0.396,
      "step": 3906
    },
    {
      "epoch": 5.12,
      "learning_rate": 7.195902688860435e-06,
      "loss": 1.6338,
      "step": 4000
    },
    {
      "epoch": 5.76,
      "learning_rate": 5.595390524967991e-06,
      "loss": 1.6186,
      "step": 4500
    },
    {
      "epoch": 6.0,
      "eval_f1": 0.912,
      "eval_gen_len": 25.419090909090908,
      "eval_loss": 1.5476245880126953,
      "eval_precision": 0.9129,
      "eval_recall": 0.9115,
      "eval_rouge1": 0.4852,
      "eval_rouge2": 0.236,
      "eval_rougeL": 0.4047,
      "eval_rougeLsum": 0.4044,
      "eval_runtime": 867.5381,
      "eval_samples_per_second": 6.34,
      "eval_steps_per_second": 0.397,
      "step": 4687
    },
    {
      "epoch": 6.4,
      "learning_rate": 3.9948783610755446e-06,
      "loss": 1.607,
      "step": 5000
    },
    {
      "epoch": 7.0,
      "eval_f1": 0.9122,
      "eval_gen_len": 25.49490909090909,
      "eval_loss": 1.5425922870635986,
      "eval_precision": 0.9129,
      "eval_recall": 0.9118,
      "eval_rouge1": 0.486,
      "eval_rouge2": 0.2367,
      "eval_rougeL": 0.4052,
      "eval_rougeLsum": 0.405,
      "eval_runtime": 866.1986,
      "eval_samples_per_second": 6.35,
      "eval_steps_per_second": 0.397,
      "step": 5468
    },
    {
      "epoch": 7.04,
      "learning_rate": 2.3943661971830984e-06,
      "loss": 1.6029,
      "step": 5500
    },
    {
      "epoch": 7.68,
      "learning_rate": 7.93854033290653e-07,
      "loss": 1.5972,
      "step": 6000
    },
    {
      "epoch": 8.0,
      "eval_f1": 0.9123,
      "eval_gen_len": 25.38509090909091,
      "eval_loss": 1.540870189666748,
      "eval_precision": 0.9131,
      "eval_recall": 0.9117,
      "eval_rouge1": 0.4869,
      "eval_rouge2": 0.2373,
      "eval_rougeL": 0.406,
      "eval_rougeLsum": 0.4058,
      "eval_runtime": 863.7281,
      "eval_samples_per_second": 6.368,
      "eval_steps_per_second": 0.398,
      "step": 6248
    },
    {
      "epoch": 8.0,
      "step": 6248,
      "total_flos": 1.1554159142381814e+18,
      "train_loss": 1.7074453571236545,
      "train_runtime": 28108.9431,
      "train_samples_per_second": 28.461,
      "train_steps_per_second": 0.222
    }
  ],
  "logging_steps": 500,
  "max_steps": 6248,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 500,
  "total_flos": 1.1554159142381814e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}