trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 345,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_gen_len": 68.04347826086956,
      "eval_loss": 0.9288747310638428,
      "eval_rouge1": 39.7591,
      "eval_rouge2": 24.1983,
      "eval_rougeL": 32.2869,
      "eval_rougeLsum": 36.1493,
      "eval_runtime": 9.3009,
      "eval_samples_per_second": 7.419,
      "eval_steps_per_second": 1.935,
      "step": 69
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 68.04347826086956,
      "eval_loss": 0.9288538694381714,
      "eval_rouge1": 39.7591,
      "eval_rouge2": 24.1983,
      "eval_rougeL": 32.2869,
      "eval_rougeLsum": 36.1493,
      "eval_runtime": 9.2625,
      "eval_samples_per_second": 7.449,
      "eval_steps_per_second": 1.943,
      "step": 138
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 68.04347826086956,
      "eval_loss": 0.9288433790206909,
      "eval_rouge1": 39.7591,
      "eval_rouge2": 24.1983,
      "eval_rougeL": 32.2869,
      "eval_rougeLsum": 36.1493,
      "eval_runtime": 9.3044,
      "eval_samples_per_second": 7.416,
      "eval_steps_per_second": 1.935,
      "step": 207
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 68.04347826086956,
      "eval_loss": 0.9288394451141357,
      "eval_rouge1": 39.7591,
      "eval_rouge2": 24.1983,
      "eval_rougeL": 32.2869,
      "eval_rougeLsum": 36.1493,
      "eval_runtime": 9.3367,
      "eval_samples_per_second": 7.39,
      "eval_steps_per_second": 1.928,
      "step": 276
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 68.04347826086956,
      "eval_loss": 0.9288389682769775,
      "eval_rouge1": 39.7591,
      "eval_rouge2": 24.1983,
      "eval_rougeL": 32.2869,
      "eval_rougeLsum": 36.1493,
      "eval_runtime": 9.2668,
      "eval_samples_per_second": 7.446,
      "eval_steps_per_second": 1.942,
      "step": 345
    },
    {
      "epoch": 5.0,
      "step": 345,
      "total_flos": 1680723777945600.0,
      "train_loss": 0.8950336843297102,
      "train_runtime": 114.301,
      "train_samples_per_second": 12.073,
      "train_steps_per_second": 3.018
    }
  ],
  "logging_steps": 500,
  "max_steps": 345,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1680723777945600.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}