{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 3620,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_gen_len": 15.835403726708075,
      "eval_loss": 4.191929817199707,
      "eval_rouge1": 14.9919,
      "eval_rouge2": 9.1411,
      "eval_rougeL": 12.8299,
      "eval_rougeLsum": 12.9602,
      "eval_runtime": 191.6694,
      "eval_samples_per_second": 1.68,
      "eval_steps_per_second": 0.214,
      "step": 362
    },
    {
      "epoch": 1.38,
      "learning_rate": 3e-05,
      "loss": 19.4803,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 10.891304347826088,
      "eval_loss": 0.8027109503746033,
      "eval_rouge1": 31.2365,
      "eval_rouge2": 23.4015,
      "eval_rougeL": 27.8979,
      "eval_rougeLsum": 28.0521,
      "eval_runtime": 167.1507,
      "eval_samples_per_second": 1.926,
      "eval_steps_per_second": 0.245,
      "step": 724
    },
    {
      "epoch": 2.76,
      "learning_rate": 2.5192307692307694e-05,
      "loss": 0.87,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 10.48136645962733,
      "eval_loss": 0.7601152658462524,
      "eval_rouge1": 32.7524,
      "eval_rouge2": 24.7831,
      "eval_rougeL": 29.4005,
      "eval_rougeLsum": 29.6329,
      "eval_runtime": 163.4166,
      "eval_samples_per_second": 1.97,
      "eval_steps_per_second": 0.251,
      "step": 1086
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 10.73913043478261,
      "eval_loss": 0.7358614802360535,
      "eval_rouge1": 32.4199,
      "eval_rouge2": 24.3103,
      "eval_rougeL": 29.045,
      "eval_rougeLsum": 29.3107,
      "eval_runtime": 165.7836,
      "eval_samples_per_second": 1.942,
      "eval_steps_per_second": 0.247,
      "step": 1448
    },
    {
      "epoch": 4.14,
      "learning_rate": 2.0384615384615387e-05,
      "loss": 0.7969,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 10.677018633540373,
      "eval_loss": 0.7158524990081787,
      "eval_rouge1": 33.081,
      "eval_rouge2": 24.9552,
      "eval_rougeL": 29.7936,
      "eval_rougeLsum": 30.0534,
      "eval_runtime": 157.6094,
      "eval_samples_per_second": 2.043,
      "eval_steps_per_second": 0.26,
      "step": 1810
    },
    {
      "epoch": 5.52,
      "learning_rate": 1.557692307692308e-05,
      "loss": 0.7607,
      "step": 2000
    },
    {
      "epoch": 6.0,
      "eval_gen_len": 10.881987577639752,
      "eval_loss": 0.7028866410255432,
      "eval_rouge1": 32.6081,
      "eval_rouge2": 24.4439,
      "eval_rougeL": 29.3121,
      "eval_rougeLsum": 29.5849,
      "eval_runtime": 172.6927,
      "eval_samples_per_second": 1.865,
      "eval_steps_per_second": 0.237,
      "step": 2172
    },
    {
      "epoch": 6.91,
      "learning_rate": 1.076923076923077e-05,
      "loss": 0.7482,
      "step": 2500
    },
    {
      "epoch": 7.0,
      "eval_gen_len": 10.881987577639752,
      "eval_loss": 0.6927917003631592,
      "eval_rouge1": 32.7673,
      "eval_rouge2": 24.6101,
      "eval_rougeL": 29.5065,
      "eval_rougeLsum": 29.7823,
      "eval_runtime": 166.0105,
      "eval_samples_per_second": 1.94,
      "eval_steps_per_second": 0.247,
      "step": 2534
    },
    {
      "epoch": 8.0,
      "eval_gen_len": 11.0,
      "eval_loss": 0.6865409016609192,
      "eval_rouge1": 32.648,
      "eval_rouge2": 24.3905,
      "eval_rougeL": 29.4374,
      "eval_rougeLsum": 29.7019,
      "eval_runtime": 167.4583,
      "eval_samples_per_second": 1.923,
      "eval_steps_per_second": 0.245,
      "step": 2896
    },
    {
      "epoch": 8.29,
      "learning_rate": 5.9615384615384615e-06,
      "loss": 0.729,
      "step": 3000
    },
    {
      "epoch": 9.0,
      "eval_gen_len": 11.003105590062113,
      "eval_loss": 0.6830553412437439,
      "eval_rouge1": 32.7058,
      "eval_rouge2": 24.4816,
      "eval_rougeL": 29.4377,
      "eval_rougeLsum": 29.6886,
      "eval_runtime": 167.3316,
      "eval_samples_per_second": 1.924,
      "eval_steps_per_second": 0.245,
      "step": 3258
    },
    {
      "epoch": 9.67,
      "learning_rate": 1.153846153846154e-06,
      "loss": 0.7218,
      "step": 3500
    },
    {
      "epoch": 10.0,
      "eval_gen_len": 10.937888198757763,
      "eval_loss": 0.6820552349090576,
      "eval_rouge1": 32.9118,
      "eval_rouge2": 24.7369,
      "eval_rougeL": 29.6106,
      "eval_rougeLsum": 29.8854,
      "eval_runtime": 166.8612,
      "eval_samples_per_second": 1.93,
      "eval_steps_per_second": 0.246,
      "step": 3620
    }
  ],
  "logging_steps": 500,
  "max_steps": 3620,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 5.047953789026304e+16,
  "trial_name": null,
  "trial_params": null
}