trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "global_step": 488,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 3e-05,
      "loss": 1.2446,
      "step": 122
    },
    {
      "epoch": 1.0,
      "eval_exact_match": 67.45385170671342,
      "eval_f1": 71.42328393297448,
      "eval_runtime": 3.9423,
      "eval_samples_per_second": 2459.708,
      "eval_steps_per_second": 7.863,
      "step": 122
    },
    {
      "epoch": 2.0,
      "learning_rate": 3e-05,
      "loss": 0.5623,
      "step": 244
    },
    {
      "epoch": 2.0,
      "eval_exact_match": 70.20728060224812,
      "eval_f1": 72.93459948557941,
      "eval_runtime": 3.4056,
      "eval_samples_per_second": 2847.343,
      "eval_steps_per_second": 9.103,
      "step": 244
    },
    {
      "epoch": 3.0,
      "learning_rate": 3e-05,
      "loss": 0.4867,
      "step": 366
    },
    {
      "epoch": 3.0,
      "eval_exact_match": 70.83634113643394,
      "eval_f1": 73.35711433093533,
      "eval_runtime": 3.3825,
      "eval_samples_per_second": 2866.828,
      "eval_steps_per_second": 9.165,
      "step": 366
    },
    {
      "epoch": 4.0,
      "learning_rate": 3e-05,
      "loss": 0.4467,
      "step": 488
    },
    {
      "epoch": 4.0,
      "eval_exact_match": 70.85696607198102,
      "eval_f1": 73.51663870716152,
      "eval_runtime": 3.3989,
      "eval_samples_per_second": 2852.98,
      "eval_steps_per_second": 9.121,
      "step": 488
    }
  ],
  "max_steps": 1220,
  "num_train_epochs": 10,
  "total_flos": 58466195472384.0,
  "trial_name": null,
  "trial_params": null
}