trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 6250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.599744e-05,
      "loss": 1.791,
      "step": 1
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 2.0203,
      "step": 6250
    },
    {
      "epoch": 1.0,
      "eval_HasAns_exact": 22.97081167532987,
      "eval_HasAns_f1": 29.82730501295977,
      "eval_HasAns_total": 5002,
      "eval_NoAns_exact": 61.644657863145255,
      "eval_NoAns_f1": 61.644657863145255,
      "eval_NoAns_total": 4998,
      "eval_best_exact": 50.0,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 50.00666666666667,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 42.3,
      "eval_f1": 45.72961796748245,
      "eval_runtime": 181.2848,
      "eval_samples_per_second": 55.162,
      "eval_steps_per_second": 6.895,
      "eval_total": 10000,
      "step": 6250
    },
    {
      "epoch": 1.0,
      "step": 6250,
      "total_flos": 45741081600000.0,
      "train_loss": 2.0202971784210204,
      "train_runtime": 3140.5446,
      "train_samples_per_second": 15.921,
      "train_steps_per_second": 1.99
    }
  ],
  "logging_steps": 500,
  "max_steps": 6250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "total_flos": 45741081600000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}