{
  "best_metric": 0.09195627272129059,
  "best_model_checkpoint": "/content/drive/MyDrive/chatbot_info/models/bilstm_ner/checkpoint-7194",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 11990,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2085070892410342,
      "grad_norm": 1.1974992752075195,
      "learning_rate": 1.9165971643035866e-05,
      "loss": 0.3538,
      "step": 500
    },
    {
      "epoch": 0.4170141784820684,
      "grad_norm": 0.7257668972015381,
      "learning_rate": 1.8331943286071728e-05,
      "loss": 0.1415,
      "step": 1000
    },
    {
      "epoch": 0.6255212677231026,
      "grad_norm": 0.9772794842720032,
      "learning_rate": 1.7497914929107593e-05,
      "loss": 0.121,
      "step": 1500
    },
    {
      "epoch": 0.8340283569641368,
      "grad_norm": 0.7119922637939453,
      "learning_rate": 1.6663886572143454e-05,
      "loss": 0.1167,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9700635783910071,
      "eval_f1": 0.8221168895049858,
      "eval_loss": 0.1039084866642952,
      "eval_precision": 0.8215658235767271,
      "eval_recall": 0.8226686951852514,
      "eval_runtime": 33.3276,
      "eval_samples_per_second": 287.75,
      "eval_steps_per_second": 18.003,
      "step": 2398
    },
    {
      "epoch": 1.042535446205171,
      "grad_norm": 0.8703278303146362,
      "learning_rate": 1.5829858215179316e-05,
      "loss": 0.1042,
      "step": 2500
    },
    {
      "epoch": 1.2510425354462051,
      "grad_norm": 0.5966465473175049,
      "learning_rate": 1.499582985821518e-05,
      "loss": 0.0928,
      "step": 3000
    },
    {
      "epoch": 1.4595496246872393,
      "grad_norm": 0.6188527345657349,
      "learning_rate": 1.4161801501251045e-05,
      "loss": 0.0894,
      "step": 3500
    },
    {
      "epoch": 1.6680567139282736,
      "grad_norm": 0.8101356625556946,
      "learning_rate": 1.3327773144286907e-05,
      "loss": 0.087,
      "step": 4000
    },
    {
      "epoch": 1.8765638031693077,
      "grad_norm": 0.9334137439727783,
      "learning_rate": 1.249374478732277e-05,
      "loss": 0.0865,
      "step": 4500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9718397518144737,
      "eval_f1": 0.8323142155768801,
      "eval_loss": 0.09386646002531052,
      "eval_precision": 0.8302021191345383,
      "eval_recall": 0.8344370860927153,
      "eval_runtime": 41.7135,
      "eval_samples_per_second": 229.901,
      "eval_steps_per_second": 14.384,
      "step": 4796
    },
    {
      "epoch": 2.085070892410342,
      "grad_norm": 0.7590944766998291,
      "learning_rate": 1.1659716430358635e-05,
      "loss": 0.0819,
      "step": 5000
    },
    {
      "epoch": 2.293577981651376,
      "grad_norm": 1.2667491436004639,
      "learning_rate": 1.0825688073394496e-05,
      "loss": 0.0709,
      "step": 5500
    },
    {
      "epoch": 2.5020850708924103,
      "grad_norm": 0.7721763849258423,
      "learning_rate": 9.99165971643036e-06,
      "loss": 0.0715,
      "step": 6000
    },
    {
      "epoch": 2.7105921601334444,
      "grad_norm": 0.8234202861785889,
      "learning_rate": 9.157631359466222e-06,
      "loss": 0.071,
      "step": 6500
    },
    {
      "epoch": 2.9190992493744785,
      "grad_norm": 0.7711541056632996,
      "learning_rate": 8.323603002502085e-06,
      "loss": 0.0686,
      "step": 7000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9727254447614853,
      "eval_f1": 0.8379830958274792,
      "eval_loss": 0.09195627272129059,
      "eval_precision": 0.8352820877606366,
      "eval_recall": 0.840701628781099,
      "eval_runtime": 39.324,
      "eval_samples_per_second": 243.871,
      "eval_steps_per_second": 15.258,
      "step": 7194
    },
    {
      "epoch": 3.127606338615513,
      "grad_norm": 0.6545294523239136,
      "learning_rate": 7.4895746455379494e-06,
      "loss": 0.062,
      "step": 7500
    },
    {
      "epoch": 3.336113427856547,
      "grad_norm": 0.6319155097007751,
      "learning_rate": 6.655546288573812e-06,
      "loss": 0.0584,
      "step": 8000
    },
    {
      "epoch": 3.5446205170975813,
      "grad_norm": 0.9260782599449158,
      "learning_rate": 5.821517931609675e-06,
      "loss": 0.0586,
      "step": 8500
    },
    {
      "epoch": 3.7531276063386154,
      "grad_norm": 0.8304509520530701,
      "learning_rate": 4.987489574645538e-06,
      "loss": 0.0577,
      "step": 9000
    },
    {
      "epoch": 3.96163469557965,
      "grad_norm": 0.9533994793891907,
      "learning_rate": 4.153461217681402e-06,
      "loss": 0.0552,
      "step": 9500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9727972577031349,
      "eval_f1": 0.8390449750138812,
      "eval_loss": 0.09282902628183365,
      "eval_precision": 0.8329585042113155,
      "eval_recall": 0.845221048863433,
      "eval_runtime": 36.8085,
      "eval_samples_per_second": 260.538,
      "eval_steps_per_second": 16.301,
      "step": 9592
    },
    {
      "epoch": 4.170141784820684,
      "grad_norm": 0.8649327754974365,
      "learning_rate": 3.319432860717265e-06,
      "loss": 0.0499,
      "step": 10000
    },
    {
      "epoch": 4.378648874061718,
      "grad_norm": 1.5371888875961304,
      "learning_rate": 2.4854045037531278e-06,
      "loss": 0.0502,
      "step": 10500
    },
    {
      "epoch": 4.587155963302752,
      "grad_norm": 0.7297742366790771,
      "learning_rate": 1.6513761467889911e-06,
      "loss": 0.0475,
      "step": 11000
    },
    {
      "epoch": 4.795663052543786,
      "grad_norm": 0.8624579310417175,
      "learning_rate": 8.173477898248542e-07,
      "loss": 0.0469,
      "step": 11500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.97306535935196,
      "eval_f1": 0.8401763448521553,
      "eval_loss": 0.09531266242265701,
      "eval_precision": 0.8361549370678958,
      "eval_recall": 0.8442366207266869,
      "eval_runtime": 38.8622,
      "eval_samples_per_second": 246.769,
      "eval_steps_per_second": 15.439,
      "step": 11990
    }
  ],
  "logging_steps": 500,
  "max_steps": 11990,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}