trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.6666666666666665,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_gen_len": 18.877,
      "eval_loss": 3.9956815242767334,
      "eval_rouge1": 3.640356760886191,
      "eval_rouge2": 1.3241316461316452,
      "eval_rougeL": 3.6251379927262484,
      "eval_rougeLsum": 3.627662198912217,
      "eval_runtime": 1371.7269,
      "eval_samples_per_second": 3.645,
      "eval_steps_per_second": 0.456,
      "step": 375
    },
    {
      "epoch": 1.33,
      "grad_norm": 11.406363487243652,
      "learning_rate": 6.680896478121665e-06,
      "loss": 4.77,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 6.1788,
      "eval_loss": 2.728412389755249,
      "eval_rouge1": 11.110740703740731,
      "eval_rouge2": 3.642182539682537,
      "eval_rougeL": 11.095423465423494,
      "eval_rougeLsum": 11.097078588078615,
      "eval_runtime": 1076.8457,
      "eval_samples_per_second": 4.643,
      "eval_steps_per_second": 0.58,
      "step": 750
    },
    {
      "epoch": 2.67,
      "grad_norm": 14.748087882995605,
      "learning_rate": 4.0128068303094986e-06,
      "loss": 2.9857,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 2625,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "total_flos": 4877098942464000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}