{
  "best_global_step": 4512,
  "best_metric": 0.6173886673369102,
  "best_model_checkpoint": "./results-freezed-seed-1337/checkpoint-4512",
  "epoch": 12.0,
  "eval_steps": 500,
  "global_step": 4512,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8514221556886228,
      "eval_f1": 0.5200098481984468,
      "eval_loss": 0.41102635860443115,
      "eval_precision": 0.6923180742188034,
      "eval_recall": 0.4806756140132551,
      "eval_runtime": 4.5834,
      "eval_samples_per_second": 582.968,
      "eval_steps_per_second": 9.163,
      "step": 376
    },
    {
      "epoch": 1.3297872340425532,
      "grad_norm": 0.7757077217102051,
      "learning_rate": 9.98e-05,
      "loss": 0.495,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8577844311377245,
      "eval_f1": 0.5730788120751112,
      "eval_loss": 0.39201080799102783,
      "eval_precision": 0.6977099441536995,
      "eval_recall": 0.5293901508987233,
      "eval_runtime": 4.604,
      "eval_samples_per_second": 580.37,
      "eval_steps_per_second": 9.123,
      "step": 752
    },
    {
      "epoch": 2.6595744680851063,
      "grad_norm": 1.0780051946640015,
      "learning_rate": 9.727322404371585e-05,
      "loss": 0.3715,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8562874251497006,
      "eval_f1": 0.5806868386243386,
      "eval_loss": 0.39746958017349243,
      "eval_precision": 0.712392115222304,
      "eval_recall": 0.5741099719517916,
      "eval_runtime": 4.5817,
      "eval_samples_per_second": 583.191,
      "eval_steps_per_second": 9.167,
      "step": 1128
    },
    {
      "epoch": 3.9893617021276597,
      "grad_norm": 1.1657006740570068,
      "learning_rate": 9.454098360655738e-05,
      "loss": 0.3742,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8581586826347305,
      "eval_f1": 0.5920838495005096,
      "eval_loss": 0.38324663043022156,
      "eval_precision": 0.6939596170509158,
      "eval_recall": 0.5721612756031641,
      "eval_runtime": 4.5777,
      "eval_samples_per_second": 583.698,
      "eval_steps_per_second": 9.175,
      "step": 1504
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8626497005988024,
      "eval_f1": 0.6006349511818206,
      "eval_loss": 0.38067346811294556,
      "eval_precision": 0.7274851647000302,
      "eval_recall": 0.5764902405636445,
      "eval_runtime": 4.5968,
      "eval_samples_per_second": 581.279,
      "eval_steps_per_second": 9.137,
      "step": 1880
    },
    {
      "epoch": 5.319148936170213,
      "grad_norm": 0.9436430335044861,
      "learning_rate": 9.180874316939892e-05,
      "loss": 0.3653,
      "step": 2000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8611526946107785,
      "eval_f1": 0.5985470178350242,
      "eval_loss": 0.3742508888244629,
      "eval_precision": 0.6949008756795468,
      "eval_recall": 0.5653264792318812,
      "eval_runtime": 4.5845,
      "eval_samples_per_second": 582.836,
      "eval_steps_per_second": 9.161,
      "step": 2256
    },
    {
      "epoch": 6.648936170212766,
      "grad_norm": 0.9061560034751892,
      "learning_rate": 8.907650273224044e-05,
      "loss": 0.3549,
      "step": 2500
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8637724550898204,
      "eval_f1": 0.6031509777257861,
      "eval_loss": 0.37474435567855835,
      "eval_precision": 0.7055885161401955,
      "eval_recall": 0.5722105753552295,
      "eval_runtime": 4.5864,
      "eval_samples_per_second": 582.595,
      "eval_steps_per_second": 9.158,
      "step": 2632
    },
    {
      "epoch": 7.9787234042553195,
      "grad_norm": 1.1018545627593994,
      "learning_rate": 8.634426229508197e-05,
      "loss": 0.3629,
      "step": 3000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8600299401197605,
      "eval_f1": 0.5634030324961963,
      "eval_loss": 0.3930947184562683,
      "eval_precision": 0.7388251505680451,
      "eval_recall": 0.5248301631518656,
      "eval_runtime": 4.5855,
      "eval_samples_per_second": 582.709,
      "eval_steps_per_second": 9.159,
      "step": 3008
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8622754491017964,
      "eval_f1": 0.6073500599359862,
      "eval_loss": 0.37540125846862793,
      "eval_precision": 0.7171149745776613,
      "eval_recall": 0.5780268292760754,
      "eval_runtime": 4.5802,
      "eval_samples_per_second": 583.383,
      "eval_steps_per_second": 9.17,
      "step": 3384
    },
    {
      "epoch": 9.308510638297872,
      "grad_norm": 0.7780441641807556,
      "learning_rate": 8.361202185792351e-05,
      "loss": 0.3501,
      "step": 3500
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.8611526946107785,
      "eval_f1": 0.5852506203922853,
      "eval_loss": 0.37850335240364075,
      "eval_precision": 0.7259173963793549,
      "eval_recall": 0.5616111286611846,
      "eval_runtime": 4.5776,
      "eval_samples_per_second": 583.717,
      "eval_steps_per_second": 9.175,
      "step": 3760
    },
    {
      "epoch": 10.638297872340425,
      "grad_norm": 0.9797687530517578,
      "learning_rate": 8.087978142076503e-05,
      "loss": 0.3546,
      "step": 4000
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.8619011976047904,
      "eval_f1": 0.5814284313893647,
      "eval_loss": 0.3815386891365051,
      "eval_precision": 0.7212152666879591,
      "eval_recall": 0.5368830750281599,
      "eval_runtime": 4.5836,
      "eval_samples_per_second": 582.951,
      "eval_steps_per_second": 9.163,
      "step": 4136
    },
    {
      "epoch": 11.96808510638298,
      "grad_norm": 0.7723910808563232,
      "learning_rate": 7.814754098360655e-05,
      "loss": 0.3452,
      "step": 4500
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.8656437125748503,
      "eval_f1": 0.6173886673369102,
      "eval_loss": 0.36994901299476624,
      "eval_precision": 0.7115342814799931,
      "eval_recall": 0.5872418942592114,
      "eval_runtime": 4.5837,
      "eval_samples_per_second": 582.931,
      "eval_steps_per_second": 9.163,
      "step": 4512
    }
  ],
  "logging_steps": 500,
  "max_steps": 18800,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9487869843271680.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}