{
  "best_global_step": 4512,
  "best_metric": 0.6166987217288957,
  "best_model_checkpoint": "./results-freezed-seed-6969/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": 0.8510479041916168,
      "eval_f1": 0.5188233379385703,
      "eval_loss": 0.412404328584671,
      "eval_precision": 0.6887281002079136,
      "eval_recall": 0.4794410461120206,
      "eval_runtime": 4.5198,
      "eval_samples_per_second": 591.181,
      "eval_steps_per_second": 9.293,
      "step": 376
    },
    {
      "epoch": 1.3297872340425532,
      "grad_norm": 0.7580151557922363,
      "learning_rate": 9.98e-05,
      "loss": 0.4997,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8562874251497006,
      "eval_f1": 0.5689887233924689,
      "eval_loss": 0.39307722449302673,
      "eval_precision": 0.687569748053619,
      "eval_recall": 0.5266166010932101,
      "eval_runtime": 4.5316,
      "eval_samples_per_second": 589.632,
      "eval_steps_per_second": 9.268,
      "step": 752
    },
    {
      "epoch": 2.6595744680851063,
      "grad_norm": 1.0576425790786743,
      "learning_rate": 9.727322404371585e-05,
      "loss": 0.3714,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8559131736526946,
      "eval_f1": 0.5818129831345137,
      "eval_loss": 0.3961324989795685,
      "eval_precision": 0.7151325535790987,
      "eval_recall": 0.5721308022936351,
      "eval_runtime": 4.5058,
      "eval_samples_per_second": 593.008,
      "eval_steps_per_second": 9.321,
      "step": 1128
    },
    {
      "epoch": 3.9893617021276597,
      "grad_norm": 1.1340179443359375,
      "learning_rate": 9.454098360655738e-05,
      "loss": 0.3744,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8607784431137725,
      "eval_f1": 0.5989395235334739,
      "eval_loss": 0.3834174573421478,
      "eval_precision": 0.7108143819134923,
      "eval_recall": 0.5768115664557467,
      "eval_runtime": 4.5202,
      "eval_samples_per_second": 591.121,
      "eval_steps_per_second": 9.292,
      "step": 1504
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8630239520958084,
      "eval_f1": 0.5987124405203501,
      "eval_loss": 0.38012266159057617,
      "eval_precision": 0.7223505874677526,
      "eval_recall": 0.5712306430666042,
      "eval_runtime": 4.5115,
      "eval_samples_per_second": 592.269,
      "eval_steps_per_second": 9.31,
      "step": 1880
    },
    {
      "epoch": 5.319148936170213,
      "grad_norm": 0.933506965637207,
      "learning_rate": 9.180874316939892e-05,
      "loss": 0.3659,
      "step": 2000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8592814371257484,
      "eval_f1": 0.5928244790291561,
      "eval_loss": 0.3744014799594879,
      "eval_precision": 0.6865504890362129,
      "eval_recall": 0.5591536397257083,
      "eval_runtime": 4.5207,
      "eval_samples_per_second": 591.061,
      "eval_steps_per_second": 9.291,
      "step": 2256
    },
    {
      "epoch": 6.648936170212766,
      "grad_norm": 0.8730207085609436,
      "learning_rate": 8.907650273224044e-05,
      "loss": 0.3555,
      "step": 2500
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8626497005988024,
      "eval_f1": 0.6020826153439911,
      "eval_loss": 0.37463295459747314,
      "eval_precision": 0.7012962512912608,
      "eval_recall": 0.5681000290373944,
      "eval_runtime": 4.5095,
      "eval_samples_per_second": 592.525,
      "eval_steps_per_second": 9.314,
      "step": 2632
    },
    {
      "epoch": 7.9787234042553195,
      "grad_norm": 1.1565885543823242,
      "learning_rate": 8.634426229508197e-05,
      "loss": 0.3634,
      "step": 3000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8592814371257484,
      "eval_f1": 0.5600785912802647,
      "eval_loss": 0.3952018916606903,
      "eval_precision": 0.7409860335210962,
      "eval_recall": 0.5220232682066058,
      "eval_runtime": 4.5084,
      "eval_samples_per_second": 592.671,
      "eval_steps_per_second": 9.316,
      "step": 3008
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8604041916167665,
      "eval_f1": 0.6007831220499781,
      "eval_loss": 0.375332772731781,
      "eval_precision": 0.7087979954051029,
      "eval_recall": 0.5722608323840338,
      "eval_runtime": 4.5089,
      "eval_samples_per_second": 592.605,
      "eval_steps_per_second": 9.315,
      "step": 3384
    },
    {
      "epoch": 9.308510638297872,
      "grad_norm": 0.7825000286102295,
      "learning_rate": 8.361202185792351e-05,
      "loss": 0.3507,
      "step": 3500
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.8622754491017964,
      "eval_f1": 0.5922042178515996,
      "eval_loss": 0.37907975912094116,
      "eval_precision": 0.7326262784423546,
      "eval_recall": 0.567072711550182,
      "eval_runtime": 4.5166,
      "eval_samples_per_second": 591.594,
      "eval_steps_per_second": 9.299,
      "step": 3760
    },
    {
      "epoch": 10.638297872340425,
      "grad_norm": 0.9841243028640747,
      "learning_rate": 8.087978142076503e-05,
      "loss": 0.3557,
      "step": 4000
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.8619011976047904,
      "eval_f1": 0.5805935400886648,
      "eval_loss": 0.38299164175987244,
      "eval_precision": 0.7313354075263248,
      "eval_recall": 0.534718353228735,
      "eval_runtime": 4.5139,
      "eval_samples_per_second": 591.949,
      "eval_steps_per_second": 9.305,
      "step": 4136
    },
    {
      "epoch": 11.96808510638298,
      "grad_norm": 0.8043486475944519,
      "learning_rate": 7.814754098360655e-05,
      "loss": 0.3462,
      "step": 4500
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.8648952095808383,
      "eval_f1": 0.6166987217288957,
      "eval_loss": 0.3703169822692871,
      "eval_precision": 0.7199382884314391,
      "eval_recall": 0.5858551193564548,
      "eval_runtime": 4.5215,
      "eval_samples_per_second": 590.952,
      "eval_steps_per_second": 9.289,
      "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
}