{
  "best_metric": 0.9320297951582869,
  "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-4350",
  "epoch": 9.988518943742825,
  "eval_steps": 500,
  "global_step": 4350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9988518943742825,
      "eval_accuracy": 0.9981441687829654,
      "eval_f1": 0.8958333333333334,
      "eval_loss": 0.006047643255442381,
      "eval_precision": 0.8713656387665198,
      "eval_recall": 0.9217148182665424,
      "eval_runtime": 14.9983,
      "eval_samples_per_second": 463.12,
      "eval_steps_per_second": 57.94,
      "step": 435
    },
    {
      "epoch": 1.148105625717566,
      "grad_norm": 0.025908155366778374,
      "learning_rate": 4.4252873563218394e-05,
      "loss": 0.0156,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9986604526553735,
      "eval_f1": 0.92,
      "eval_loss": 0.004434330388903618,
      "eval_precision": 0.9182915506035283,
      "eval_recall": 0.9217148182665424,
      "eval_runtime": 15.157,
      "eval_samples_per_second": 458.27,
      "eval_steps_per_second": 57.333,
      "step": 871
    },
    {
      "epoch": 2.296211251435132,
      "grad_norm": 0.015398409217596054,
      "learning_rate": 3.850574712643678e-05,
      "loss": 0.0038,
      "step": 1000
    },
    {
      "epoch": 2.9988518943742823,
      "eval_accuracy": 0.9986883598917199,
      "eval_f1": 0.9181073703366698,
      "eval_loss": 0.0040275463834404945,
      "eval_precision": 0.8968888888888888,
      "eval_recall": 0.940354147250699,
      "eval_runtime": 15.1362,
      "eval_samples_per_second": 458.9,
      "eval_steps_per_second": 57.412,
      "step": 1306
    },
    {
      "epoch": 3.444316877152698,
      "grad_norm": 0.024467067793011665,
      "learning_rate": 3.275862068965517e-05,
      "loss": 0.0025,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9985837077554209,
      "eval_f1": 0.9215236346948141,
      "eval_loss": 0.004492571111768484,
      "eval_precision": 0.9077757685352622,
      "eval_recall": 0.9356943150046598,
      "eval_runtime": 15.2768,
      "eval_samples_per_second": 454.675,
      "eval_steps_per_second": 56.884,
      "step": 1742
    },
    {
      "epoch": 4.592422502870264,
      "grad_norm": 0.014663909561932087,
      "learning_rate": 2.7011494252873566e-05,
      "loss": 0.0016,
      "step": 2000
    },
    {
      "epoch": 4.998851894374282,
      "eval_accuracy": 0.9985906845645076,
      "eval_f1": 0.9138576779026217,
      "eval_loss": 0.0054086255840957165,
      "eval_precision": 0.9181561618062088,
      "eval_recall": 0.9095992544268406,
      "eval_runtime": 15.0107,
      "eval_samples_per_second": 462.737,
      "eval_steps_per_second": 57.892,
      "step": 2177
    },
    {
      "epoch": 5.7405281285878305,
      "grad_norm": 0.002929804613813758,
      "learning_rate": 2.1264367816091954e-05,
      "loss": 0.0011,
      "step": 2500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9986395222281137,
      "eval_f1": 0.9202965708989805,
      "eval_loss": 0.00529602263122797,
      "eval_precision": 0.9152073732718894,
      "eval_recall": 0.9254426840633737,
      "eval_runtime": 15.2091,
      "eval_samples_per_second": 456.701,
      "eval_steps_per_second": 57.137,
      "step": 2613
    },
    {
      "epoch": 6.888633754305396,
      "grad_norm": 0.06796916574239731,
      "learning_rate": 1.5517241379310346e-05,
      "loss": 0.0009,
      "step": 3000
    },
    {
      "epoch": 6.998851894374282,
      "eval_accuracy": 0.9986604526553735,
      "eval_f1": 0.9314179796107507,
      "eval_loss": 0.006041177082806826,
      "eval_precision": 0.9262672811059908,
      "eval_recall": 0.9366262814538676,
      "eval_runtime": 15.0006,
      "eval_samples_per_second": 463.048,
      "eval_steps_per_second": 57.931,
      "step": 3048
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9987511511734993,
      "eval_f1": 0.9290976058931859,
      "eval_loss": 0.005891016684472561,
      "eval_precision": 0.9181073703366697,
      "eval_recall": 0.940354147250699,
      "eval_runtime": 15.2005,
      "eval_samples_per_second": 456.957,
      "eval_steps_per_second": 57.169,
      "step": 3484
    },
    {
      "epoch": 8.036739380022961,
      "grad_norm": 0.0015728959115222096,
      "learning_rate": 9.770114942528738e-06,
      "loss": 0.0005,
      "step": 3500
    },
    {
      "epoch": 8.998851894374283,
      "eval_accuracy": 0.9987581279825859,
      "eval_f1": 0.9279404927940494,
      "eval_loss": 0.006726197898387909,
      "eval_precision": 0.9257884972170687,
      "eval_recall": 0.9301025163094129,
      "eval_runtime": 15.4019,
      "eval_samples_per_second": 450.984,
      "eval_steps_per_second": 56.422,
      "step": 3919
    },
    {
      "epoch": 9.184845005740527,
      "grad_norm": 0.11025261133909225,
      "learning_rate": 4.022988505747127e-06,
      "loss": 0.0003,
      "step": 4000
    },
    {
      "epoch": 9.988518943742825,
      "eval_accuracy": 0.998772081600759,
      "eval_f1": 0.9320297951582869,
      "eval_loss": 0.007080046460032463,
      "eval_precision": 0.9311627906976744,
      "eval_recall": 0.9328984156570364,
      "eval_runtime": 15.2679,
      "eval_samples_per_second": 454.941,
      "eval_steps_per_second": 56.917,
      "step": 4350
    },
    {
      "epoch": 9.988518943742825,
      "step": 4350,
      "total_flos": 1.1084127968547612e+16,
      "train_loss": 0.003044272955806776,
      "train_runtime": 1809.5975,
      "train_samples_per_second": 153.852,
      "train_steps_per_second": 2.404
    }
  ],
  "logging_steps": 500,
  "max_steps": 4350,
  "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": 1.1084127968547612e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}