{
  "best_metric": 0.987703144062033,
  "best_model_checkpoint": "./model/checkpoint-2224",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 5560,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8992805755395683,
      "grad_norm": 15.831398963928223,
      "learning_rate": 2.731834532374101e-05,
      "loss": 0.1341,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9858275687531635,
      "eval_f1": 0.9858428119593087,
      "eval_loss": 0.06046506017446518,
      "eval_precision": 0.9858980040864742,
      "eval_recall": 0.9858275687531635,
      "eval_runtime": 123.5336,
      "eval_samples_per_second": 47.979,
      "eval_steps_per_second": 1.506,
      "step": 556
    },
    {
      "epoch": 1.7985611510791366,
      "grad_norm": 0.1419404149055481,
      "learning_rate": 2.4620503597122304e-05,
      "loss": 0.0458,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9844778133963219,
      "eval_f1": 0.9844685311325714,
      "eval_loss": 0.06095171347260475,
      "eval_precision": 0.984470890080927,
      "eval_recall": 0.9844778133963219,
      "eval_runtime": 324.024,
      "eval_samples_per_second": 18.292,
      "eval_steps_per_second": 0.574,
      "step": 1112
    },
    {
      "epoch": 2.697841726618705,
      "grad_norm": 0.0644543468952179,
      "learning_rate": 2.1928057553956834e-05,
      "loss": 0.0255,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9856588493335583,
      "eval_f1": 0.9856725274058569,
      "eval_loss": 0.06607956439256668,
      "eval_precision": 0.985717476255087,
      "eval_recall": 0.9856588493335583,
      "eval_runtime": 23.8528,
      "eval_samples_per_second": 248.482,
      "eval_steps_per_second": 7.798,
      "step": 1668
    },
    {
      "epoch": 3.597122302158273,
      "grad_norm": 0.006873908918350935,
      "learning_rate": 1.923021582733813e-05,
      "loss": 0.0098,
      "step": 2000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9876834823688206,
      "eval_f1": 0.987703144062033,
      "eval_loss": 0.06861425936222076,
      "eval_precision": 0.9878126950690342,
      "eval_recall": 0.9876834823688206,
      "eval_runtime": 123.3642,
      "eval_samples_per_second": 48.045,
      "eval_steps_per_second": 1.508,
      "step": 2224
    },
    {
      "epoch": 4.496402877697841,
      "grad_norm": 0.0038243578746914864,
      "learning_rate": 1.653776978417266e-05,
      "loss": 0.0051,
      "step": 2500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.98279061920027,
      "eval_f1": 0.9827652293288254,
      "eval_loss": 0.11865255236625671,
      "eval_precision": 0.9828086020917639,
      "eval_recall": 0.98279061920027,
      "eval_runtime": 123.5475,
      "eval_samples_per_second": 47.973,
      "eval_steps_per_second": 1.505,
      "step": 2780
    },
    {
      "epoch": 5.39568345323741,
      "grad_norm": 0.00035207424662075937,
      "learning_rate": 1.3839928057553959e-05,
      "loss": 0.0012,
      "step": 3000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9844778133963219,
      "eval_f1": 0.9844549127279602,
      "eval_loss": 0.10734612494707108,
      "eval_precision": 0.9845009079108045,
      "eval_recall": 0.9844778133963219,
      "eval_runtime": 324.4042,
      "eval_samples_per_second": 18.27,
      "eval_steps_per_second": 0.573,
      "step": 3336
    },
    {
      "epoch": 6.294964028776978,
      "grad_norm": 0.0010561492526903749,
      "learning_rate": 1.1142086330935252e-05,
      "loss": 0.0006,
      "step": 3500
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9844778133963219,
      "eval_f1": 0.9844617747386799,
      "eval_loss": 0.1119009479880333,
      "eval_precision": 0.9844800053876499,
      "eval_recall": 0.9844778133963219,
      "eval_runtime": 123.6461,
      "eval_samples_per_second": 47.935,
      "eval_steps_per_second": 1.504,
      "step": 3892
    },
    {
      "epoch": 7.194244604316546,
      "grad_norm": 0.0001651465572649613,
      "learning_rate": 8.444244604316547e-06,
      "loss": 0.0,
      "step": 4000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9843090939767167,
      "eval_f1": 0.9842866428636935,
      "eval_loss": 0.12110123783349991,
      "eval_precision": 0.9843290706362859,
      "eval_recall": 0.9843090939767167,
      "eval_runtime": 323.8258,
      "eval_samples_per_second": 18.303,
      "eval_steps_per_second": 0.574,
      "step": 4448
    },
    {
      "epoch": 8.093525179856115,
      "grad_norm": 0.0001012256761896424,
      "learning_rate": 5.7464028776978415e-06,
      "loss": 0.0001,
      "step": 4500
    },
    {
      "epoch": 8.992805755395683,
      "grad_norm": 0.00017143118020612746,
      "learning_rate": 3.048561151079137e-06,
      "loss": 0.0002,
      "step": 5000
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9849839716551375,
      "eval_f1": 0.9849730419562784,
      "eval_loss": 0.11790579557418823,
      "eval_precision": 0.9849792957695417,
      "eval_recall": 0.9849839716551375,
      "eval_runtime": 324.0234,
      "eval_samples_per_second": 18.292,
      "eval_steps_per_second": 0.574,
      "step": 5004
    },
    {
      "epoch": 9.892086330935252,
      "grad_norm": 0.00013196947111282498,
      "learning_rate": 3.507194244604317e-07,
      "loss": 0.0001,
      "step": 5500
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9849839716551375,
      "eval_f1": 0.9849833368509429,
      "eval_loss": 0.11824283748865128,
      "eval_precision": 0.9849827613456668,
      "eval_recall": 0.9849839716551375,
      "eval_runtime": 223.7176,
      "eval_samples_per_second": 26.493,
      "eval_steps_per_second": 0.831,
      "step": 5560
    }
  ],
  "logging_steps": 500,
  "max_steps": 5560,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.14246287551488e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}