{
  "best_metric": 0.9521203830369357,
  "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-2440",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 4880,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9987641945981572,
      "eval_f1": 0.9355123674911661,
      "eval_loss": 0.003916793502867222,
      "eval_precision": 0.9005102040816326,
      "eval_recall": 0.9733455882352942,
      "eval_runtime": 13.936,
      "eval_samples_per_second": 488.661,
      "eval_steps_per_second": 61.136,
      "step": 488
    },
    {
      "epoch": 1.0245901639344261,
      "grad_norm": 0.24995087087154388,
      "learning_rate": 4.487704918032787e-05,
      "loss": 0.0189,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9989495654084337,
      "eval_f1": 0.9413886384129847,
      "eval_loss": 0.0032420416828244925,
      "eval_precision": 0.9238938053097345,
      "eval_recall": 0.9595588235294118,
      "eval_runtime": 14.0058,
      "eval_samples_per_second": 486.228,
      "eval_steps_per_second": 60.832,
      "step": 976
    },
    {
      "epoch": 2.0491803278688523,
      "grad_norm": 0.04940846189856529,
      "learning_rate": 3.975409836065574e-05,
      "loss": 0.0027,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9989358342373021,
      "eval_f1": 0.9402784014369105,
      "eval_loss": 0.0043699671514332294,
      "eval_precision": 0.9192273924495171,
      "eval_recall": 0.9623161764705882,
      "eval_runtime": 14.0607,
      "eval_samples_per_second": 484.329,
      "eval_steps_per_second": 60.594,
      "step": 1464
    },
    {
      "epoch": 3.0737704918032787,
      "grad_norm": 0.01636342518031597,
      "learning_rate": 3.463114754098361e-05,
      "loss": 0.0015,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9990594147774864,
      "eval_f1": 0.9445208619899129,
      "eval_loss": 0.0036185304634273052,
      "eval_precision": 0.9423604757548033,
      "eval_recall": 0.9466911764705882,
      "eval_runtime": 14.26,
      "eval_samples_per_second": 477.56,
      "eval_steps_per_second": 59.748,
      "step": 1952
    },
    {
      "epoch": 4.098360655737705,
      "grad_norm": 0.006754329428076744,
      "learning_rate": 2.9508196721311478e-05,
      "loss": 0.0007,
      "step": 2000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9991418018042759,
      "eval_f1": 0.9521203830369357,
      "eval_loss": 0.004440780263394117,
      "eval_precision": 0.9447963800904977,
      "eval_recall": 0.9595588235294118,
      "eval_runtime": 14.0071,
      "eval_samples_per_second": 486.182,
      "eval_steps_per_second": 60.826,
      "step": 2440
    },
    {
      "epoch": 5.122950819672131,
      "grad_norm": 0.0005009469459764659,
      "learning_rate": 2.4385245901639343e-05,
      "loss": 0.0004,
      "step": 2500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9990456836063548,
      "eval_f1": 0.9464368886818817,
      "eval_loss": 0.005531433038413525,
      "eval_precision": 0.959395656279509,
      "eval_recall": 0.9338235294117647,
      "eval_runtime": 14.0724,
      "eval_samples_per_second": 483.926,
      "eval_steps_per_second": 60.544,
      "step": 2928
    },
    {
      "epoch": 6.147540983606557,
      "grad_norm": 0.7484572529792786,
      "learning_rate": 1.9262295081967212e-05,
      "loss": 0.0002,
      "step": 3000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9989907589218284,
      "eval_f1": 0.9427393495190106,
      "eval_loss": 0.004938796162605286,
      "eval_precision": 0.9397260273972603,
      "eval_recall": 0.9457720588235294,
      "eval_runtime": 13.9575,
      "eval_samples_per_second": 487.909,
      "eval_steps_per_second": 61.042,
      "step": 3416
    },
    {
      "epoch": 7.172131147540983,
      "grad_norm": 0.00041869020787999034,
      "learning_rate": 1.4139344262295081e-05,
      "loss": 0.0002,
      "step": 3500
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.999073145948618,
      "eval_f1": 0.9468864468864469,
      "eval_loss": 0.005282656755298376,
      "eval_precision": 0.9434306569343066,
      "eval_recall": 0.9503676470588235,
      "eval_runtime": 14.1087,
      "eval_samples_per_second": 482.68,
      "eval_steps_per_second": 60.388,
      "step": 3904
    },
    {
      "epoch": 8.19672131147541,
      "grad_norm": 0.004756764974445105,
      "learning_rate": 9.016393442622952e-06,
      "loss": 0.0001,
      "step": 4000
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9990525491919205,
      "eval_f1": 0.946404031149794,
      "eval_loss": 0.0050343358889222145,
      "eval_precision": 0.94337899543379,
      "eval_recall": 0.9494485294117647,
      "eval_runtime": 14.373,
      "eval_samples_per_second": 473.804,
      "eval_steps_per_second": 59.278,
      "step": 4392
    },
    {
      "epoch": 9.221311475409836,
      "grad_norm": 0.00033881032140925527,
      "learning_rate": 3.89344262295082e-06,
      "loss": 0.0001,
      "step": 4500
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9990525491919205,
      "eval_f1": 0.945537757437071,
      "eval_loss": 0.005196314305067062,
      "eval_precision": 0.9416590701914311,
      "eval_recall": 0.9494485294117647,
      "eval_runtime": 14.6459,
      "eval_samples_per_second": 464.976,
      "eval_steps_per_second": 58.173,
      "step": 4880
    },
    {
      "epoch": 10.0,
      "step": 4880,
      "total_flos": 1.5694885147146138e+16,
      "train_loss": 0.002533856062142209,
      "train_runtime": 1422.7831,
      "train_samples_per_second": 219.492,
      "train_steps_per_second": 3.43
    }
  ],
  "logging_steps": 500,
  "max_steps": 4880,
  "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": 1.5694885147146138e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}