checkpoint-2500/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.358490566037736,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.47,
      "learning_rate": 4.213836477987422e-05,
      "loss": 0.3579,
      "step": 500
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.4276729559748424e-05,
      "loss": 0.3025,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 14.745930644019817,
      "eval_loss": 0.3904925584793091,
      "eval_rouge1": 22.6674,
      "eval_rouge2": 5.4037,
      "eval_rougeL": 20.2687,
      "eval_rougeLsum": 20.297,
      "eval_runtime": 247.0796,
      "eval_samples_per_second": 5.719,
      "eval_steps_per_second": 1.433,
      "step": 1060
    },
    {
      "epoch": 1.42,
      "learning_rate": 2.641509433962264e-05,
      "loss": 0.2978,
      "step": 1500
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.8553459119496856e-05,
      "loss": 0.2772,
      "step": 2000
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 11.341825902335456,
      "eval_loss": 0.37492871284484863,
      "eval_rouge1": 24.3917,
      "eval_rouge2": 6.7944,
      "eval_rougeL": 22.2165,
      "eval_rougeLsum": 22.244,
      "eval_runtime": 263.2819,
      "eval_samples_per_second": 5.367,
      "eval_steps_per_second": 1.345,
      "step": 2120
    },
    {
      "epoch": 2.36,
      "learning_rate": 1.069182389937107e-05,
      "loss": 0.2196,
      "step": 2500
    }
  ],
  "max_steps": 3180,
  "num_train_epochs": 3,
  "total_flos": 1.8198409955196764e+18,
  "trial_name": null,
  "trial_params": null
}