{
  "best_metric": 0.8512137823022711,
  "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-4315",
  "epoch": 9.991889699918897,
  "eval_steps": 500,
  "global_step": 6160,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8110300081103001,
      "grad_norm": 0.7429273724555969,
      "learning_rate": 4.5941558441558444e-05,
      "loss": 0.0571,
      "step": 500
    },
    {
      "epoch": 0.9991889699918897,
      "eval_accuracy": 0.9906421648980531,
      "eval_f1": 0.8112888052681091,
      "eval_loss": 0.02658958174288273,
      "eval_precision": 0.776657060518732,
      "eval_recall": 0.8491532099251674,
      "eval_runtime": 15.3903,
      "eval_samples_per_second": 477.832,
      "eval_steps_per_second": 59.778,
      "step": 616
    },
    {
      "epoch": 1.6220600162206003,
      "grad_norm": 0.32481127977371216,
      "learning_rate": 4.1883116883116886e-05,
      "loss": 0.018,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9914186293963707,
      "eval_f1": 0.8270561106840891,
      "eval_loss": 0.030444670468568802,
      "eval_precision": 0.8075046904315197,
      "eval_recall": 0.8475777865301299,
      "eval_runtime": 15.7588,
      "eval_samples_per_second": 466.66,
      "eval_steps_per_second": 58.38,
      "step": 1233
    },
    {
      "epoch": 2.4330900243309004,
      "grad_norm": 0.10290508717298508,
      "learning_rate": 3.782467532467533e-05,
      "loss": 0.0101,
      "step": 1500
    },
    {
      "epoch": 2.9991889699918897,
      "eval_accuracy": 0.9906249101314238,
      "eval_f1": 0.8310784692694241,
      "eval_loss": 0.03564191609621048,
      "eval_precision": 0.8159392789373814,
      "eval_recall": 0.8467900748326113,
      "eval_runtime": 15.5516,
      "eval_samples_per_second": 472.877,
      "eval_steps_per_second": 59.158,
      "step": 1849
    },
    {
      "epoch": 3.2441200324412005,
      "grad_norm": 0.3212472200393677,
      "learning_rate": 3.376623376623377e-05,
      "loss": 0.0057,
      "step": 2000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9910217697638973,
      "eval_f1": 0.8348231636222309,
      "eval_loss": 0.03653988987207413,
      "eval_precision": 0.8239355581127733,
      "eval_recall": 0.8460023631350926,
      "eval_runtime": 15.8023,
      "eval_samples_per_second": 465.375,
      "eval_steps_per_second": 58.219,
      "step": 2466
    },
    {
      "epoch": 4.0551500405515,
      "grad_norm": 1.049054741859436,
      "learning_rate": 2.9707792207792207e-05,
      "loss": 0.0039,
      "step": 2500
    },
    {
      "epoch": 4.866180048661801,
      "grad_norm": 0.12911342084407806,
      "learning_rate": 2.5649350649350652e-05,
      "loss": 0.0027,
      "step": 3000
    },
    {
      "epoch": 4.99918896999189,
      "eval_accuracy": 0.9915624191182815,
      "eval_f1": 0.8343344313117613,
      "eval_loss": 0.03956884518265724,
      "eval_precision": 0.8211289092295957,
      "eval_recall": 0.8479716423788893,
      "eval_runtime": 15.4772,
      "eval_samples_per_second": 475.151,
      "eval_steps_per_second": 59.442,
      "step": 3082
    },
    {
      "epoch": 5.6772100567721,
      "grad_norm": 0.1811482459306717,
      "learning_rate": 2.1590909090909093e-05,
      "loss": 0.0018,
      "step": 3500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9915394127627757,
      "eval_f1": 0.846658941676323,
      "eval_loss": 0.04350048676133156,
      "eval_precision": 0.8306176582038651,
      "eval_recall": 0.8633320204805042,
      "eval_runtime": 15.4958,
      "eval_samples_per_second": 474.581,
      "eval_steps_per_second": 59.371,
      "step": 3699
    },
    {
      "epoch": 6.488240064882401,
      "grad_norm": 0.0691465437412262,
      "learning_rate": 1.7532467532467535e-05,
      "loss": 0.0013,
      "step": 4000
    },
    {
      "epoch": 6.99918896999189,
      "eval_accuracy": 0.991867253328732,
      "eval_f1": 0.8512137823022711,
      "eval_loss": 0.047813717275857925,
      "eval_precision": 0.8462436745815493,
      "eval_recall": 0.8562426152028357,
      "eval_runtime": 15.6578,
      "eval_samples_per_second": 469.669,
      "eval_steps_per_second": 58.757,
      "step": 4315
    },
    {
      "epoch": 7.299270072992701,
      "grad_norm": 0.016636306419968605,
      "learning_rate": 1.3474025974025975e-05,
      "loss": 0.0008,
      "step": 4500
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9914761452851351,
      "eval_f1": 0.8478387284357433,
      "eval_loss": 0.04689360409975052,
      "eval_precision": 0.8347328244274809,
      "eval_recall": 0.8613627412367074,
      "eval_runtime": 15.6856,
      "eval_samples_per_second": 468.838,
      "eval_steps_per_second": 58.653,
      "step": 4932
    },
    {
      "epoch": 8.110300081103,
      "grad_norm": 0.02262457087635994,
      "learning_rate": 9.415584415584416e-06,
      "loss": 0.0008,
      "step": 5000
    },
    {
      "epoch": 8.921330089213301,
      "grad_norm": 0.6416856646537781,
      "learning_rate": 5.357142857142857e-06,
      "loss": 0.0004,
      "step": 5500
    },
    {
      "epoch": 8.99918896999189,
      "eval_accuracy": 0.9918845080953613,
      "eval_f1": 0.851080397118941,
      "eval_loss": 0.05153572931885719,
      "eval_precision": 0.8414164742109315,
      "eval_recall": 0.860968885387948,
      "eval_runtime": 15.5849,
      "eval_samples_per_second": 471.866,
      "eval_steps_per_second": 59.031,
      "step": 5548
    },
    {
      "epoch": 9.732360097323602,
      "grad_norm": 0.011619620956480503,
      "learning_rate": 1.2987012987012988e-06,
      "loss": 0.0002,
      "step": 6000
    },
    {
      "epoch": 9.991889699918897,
      "eval_accuracy": 0.9917694763178329,
      "eval_f1": 0.8490859587709063,
      "eval_loss": 0.05196274444460869,
      "eval_precision": 0.8386477141759509,
      "eval_recall": 0.85978731784167,
      "eval_runtime": 15.9471,
      "eval_samples_per_second": 461.149,
      "eval_steps_per_second": 57.691,
      "step": 6160
    },
    {
      "epoch": 9.991889699918897,
      "step": 6160,
      "total_flos": 1.919784837910831e+16,
      "train_loss": 0.008344567238123386,
      "train_runtime": 1725.5138,
      "train_samples_per_second": 228.488,
      "train_steps_per_second": 3.57
    }
  ],
  "logging_steps": 500,
  "max_steps": 6160,
  "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": 1.919784837910831e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}