checkpoint-4096/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.024715768660405,
  "global_step": 4096,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.51,
      "learning_rate": 5e-05,
      "loss": 3.4077,
      "step": 1024
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.4766957759857178,
      "eval_rouge2_fmeasure": 0.0513,
      "eval_rouge2_precision": 0.0296,
      "eval_rouge2_recall": 0.2472,
      "eval_runtime": 9350.9062,
      "eval_samples_per_second": 0.865,
      "eval_steps_per_second": 0.054,
      "step": 2023
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.985133795837463e-05,
      "loss": 2.6431,
      "step": 2048
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.9702675916749255e-05,
      "loss": 2.3161,
      "step": 3072
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.278710126876831,
      "eval_rouge2_fmeasure": 0.0574,
      "eval_rouge2_precision": 0.0327,
      "eval_rouge2_recall": 0.2966,
      "eval_runtime": 9356.4308,
      "eval_samples_per_second": 0.865,
      "eval_steps_per_second": 0.054,
      "step": 4046
    },
    {
      "epoch": 2.02,
      "learning_rate": 1.9554013875123885e-05,
      "loss": 2.2142,
      "step": 4096
    }
  ],
  "max_steps": 6069,
  "num_train_epochs": 3,
  "total_flos": 1.1825437857319748e+19,
  "trial_name": null,
  "trial_params": null
}