{
  "training_log_history": [
    {
      "loss": 1.7147529602050782,
      "grad_norm": 0.5557429194450378,
      "learning_rate": 5e-05,
      "entropy": 1.3842266023159027,
      "num_tokens": 79716.0,
      "mean_token_accuracy": 0.6636141866445542,
      "epoch": 0.0010526315789473684,
      "step": 10
    },
    {
      "loss": 1.057517147064209,
      "grad_norm": 0.4807300567626953,
      "learning_rate": 9.982817869415808e-05,
      "entropy": 1.194282191991806,
      "num_tokens": 161880.0,
      "mean_token_accuracy": 0.7640660256147385,
      "epoch": 0.002105263157894737,
      "step": 20
    },
    {
      "loss": 0.8556486129760742,
      "grad_norm": 0.32483115792274475,
      "learning_rate": 9.810996563573883e-05,
      "entropy": 0.8799786627292633,
      "num_tokens": 242837.0,
      "mean_token_accuracy": 0.8109526604413986,
      "epoch": 0.003157894736842105,
      "step": 30
    },
    {
      "loss": 0.7565423011779785,
      "grad_norm": 0.28475627303123474,
      "learning_rate": 9.639175257731959e-05,
      "entropy": 0.7401942551136017,
      "num_tokens": 319859.0,
      "mean_token_accuracy": 0.8288935780525207,
      "epoch": 0.004210526315789474,
      "step": 40
    },
    {
      "loss": 0.7918671607971192,
      "grad_norm": 0.2301568239927292,
      "learning_rate": 9.467353951890035e-05,
      "entropy": 0.7903933167457581,
      "num_tokens": 397501.0,
      "mean_token_accuracy": 0.825095483660698,
      "epoch": 0.005263157894736842,
      "step": 50
    },
    {
      "loss": 0.8224129676818848,
      "grad_norm": 0.3627431392669678,
      "learning_rate": 9.29553264604811e-05,
      "entropy": 0.7655193030834198,
      "num_tokens": 473920.0,
      "mean_token_accuracy": 0.8176214396953583,
      "epoch": 0.00631578947368421,
      "step": 60
    },
    {
      "loss": 0.8464207649230957,
      "grad_norm": 0.2397315502166748,
      "learning_rate": 9.123711340206186e-05,
      "entropy": 0.8343378663063049,
      "num_tokens": 559247.0,
      "mean_token_accuracy": 0.8138128280639648,
      "epoch": 0.007368421052631579,
      "step": 70
    },
    {
      "loss": 0.7613609313964844,
      "grad_norm": 0.24598781764507294,
      "learning_rate": 8.951890034364262e-05,
      "entropy": 0.7148342356085777,
      "num_tokens": 647916.0,
      "mean_token_accuracy": 0.8272515207529068,
      "epoch": 0.008421052631578947,
      "step": 80
    },
    {
      "loss": 0.7937052249908447,
      "grad_norm": 0.3052941560745239,
      "learning_rate": 8.780068728522337e-05,
      "entropy": 0.7415616571903229,
      "num_tokens": 731904.0,
      "mean_token_accuracy": 0.818175607919693,
      "epoch": 0.009473684210526316,
      "step": 90
    },
    {
      "loss": 0.8092642784118652,
      "grad_norm": 0.21103884279727936,
      "learning_rate": 8.608247422680413e-05,
      "entropy": 0.7637654632329941,
      "num_tokens": 813854.0,
      "mean_token_accuracy": 0.8194937348365784,
      "epoch": 0.010526315789473684,
      "step": 100
    },
    {
      "eval_loss": 0.7767549753189087,
      "eval_runtime": 347.5891,
      "eval_samples_per_second": 11.508,
      "eval_steps_per_second": 2.877,
      "eval_entropy": 0.7429669258594513,
      "eval_num_tokens": 813854.0,
      "eval_mean_token_accuracy": 0.8241108784079552,
      "epoch": 0.010526315789473684,
      "step": 100
    },
    {
      "loss": 0.7675327777862548,
      "grad_norm": 0.2367396205663681,
      "learning_rate": 8.436426116838489e-05,
      "entropy": 0.7208087205886841,
      "num_tokens": 888287.0,
      "mean_token_accuracy": 0.8270161330699921,
      "epoch": 0.011578947368421053,
      "step": 110
    },
    {
      "loss": 0.8215232849121094,
      "grad_norm": 0.24846169352531433,
      "learning_rate": 8.264604810996563e-05,
      "entropy": 0.778062978386879,
      "num_tokens": 968928.0,
      "mean_token_accuracy": 0.8151075035333634,
      "epoch": 0.01263157894736842,
      "step": 120
    },
    {
      "loss": 0.8481046676635742,
      "grad_norm": 0.2661391496658325,
      "learning_rate": 8.092783505154639e-05,
      "entropy": 0.7925655305385589,
      "num_tokens": 1056013.0,
      "mean_token_accuracy": 0.8117670178413391,
      "epoch": 0.01368421052631579,
      "step": 130
    },
    {
      "loss": 0.8251470565795899,
      "grad_norm": 0.2490185648202896,
      "learning_rate": 7.920962199312715e-05,
      "entropy": 0.7860086858272552,
      "num_tokens": 1139592.0,
      "mean_token_accuracy": 0.8182792365550995,
      "epoch": 0.014736842105263158,
      "step": 140
    },
    {
      "loss": 0.8617103576660157,
      "grad_norm": 0.19872666895389557,
      "learning_rate": 7.749140893470791e-05,
      "entropy": 0.7972662836313248,
      "num_tokens": 1236037.0,
      "mean_token_accuracy": 0.8090041935443878,
      "epoch": 0.015789473684210527,
      "step": 150
    },
    {
      "loss": 0.7977757453918457,
      "grad_norm": 0.19242972135543823,
      "learning_rate": 7.577319587628867e-05,
      "entropy": 0.7521506130695343,
      "num_tokens": 1324602.0,
      "mean_token_accuracy": 0.8219349443912506,
      "epoch": 0.016842105263157894,
      "step": 160
    },
    {
      "loss": 0.8367820739746094,
      "grad_norm": 0.2736385762691498,
      "learning_rate": 7.405498281786943e-05,
      "entropy": 0.7833776384592056,
      "num_tokens": 1412212.0,
      "mean_token_accuracy": 0.8115390419960022,
      "epoch": 0.017894736842105262,
      "step": 170
    },
    {
      "loss": 0.7536766052246093,
      "grad_norm": 0.20205377042293549,
      "learning_rate": 7.233676975945017e-05,
      "entropy": 0.7218452334403992,
      "num_tokens": 1506219.0,
      "mean_token_accuracy": 0.8291705161333084,
      "epoch": 0.018947368421052633,
      "step": 180
    },
    {
      "loss": 0.7809348106384277,
      "grad_norm": 0.22076274454593658,
      "learning_rate": 7.061855670103093e-05,
      "entropy": 0.7482779085636139,
      "num_tokens": 1587426.0,
      "mean_token_accuracy": 0.8284277468919754,
      "epoch": 0.02,
      "step": 190
    }
  ],
  "generation_eval": {
    "json_validity_rate": 0.5,
    "avg_required_field_completion": 0.171875,
    "num_generation_eval_samples": 8
  },
  "generation_eval_no_think": {
    "inference_mode": "tokenizer.apply_chat_template(..., enable_thinking=False) when supported",
    "num_generation_eval_samples": 24,
    "json_validity_rate": 1.0,
    "listing_num_samples": 13,
    "listing_json_validity_rate": 1.0,
    "listing_avg_required_field_completion": 0.7980769230769231
  }
}