{
  "best_metric": 0.45455732567249935,
  "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-2705",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 5410,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9242144177449169,
      "grad_norm": 1.4528056383132935,
      "learning_rate": 4.537892791127542e-05,
      "loss": 0.3191,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8443022505389485,
      "eval_f1": 0.407486125870823,
      "eval_loss": 0.47723615169525146,
      "eval_precision": 0.27250473783954515,
      "eval_recall": 0.8074403369209172,
      "eval_runtime": 14.3908,
      "eval_samples_per_second": 473.218,
      "eval_steps_per_second": 59.204,
      "step": 541
    },
    {
      "epoch": 1.8484288354898335,
      "grad_norm": 1.5587466955184937,
      "learning_rate": 4.075785582255083e-05,
      "loss": 0.1619,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8552871874442172,
      "eval_f1": 0.43975123088883133,
      "eval_loss": 0.4583655595779419,
      "eval_precision": 0.30406737143881024,
      "eval_recall": 0.7941038839494619,
      "eval_runtime": 14.212,
      "eval_samples_per_second": 479.173,
      "eval_steps_per_second": 59.949,
      "step": 1082
    },
    {
      "epoch": 2.7726432532347505,
      "grad_norm": 0.9616082310676575,
      "learning_rate": 3.613678373382625e-05,
      "loss": 0.11,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8435470361267112,
      "eval_f1": 0.4338006724608259,
      "eval_loss": 0.6447410583496094,
      "eval_precision": 0.29758899817216466,
      "eval_recall": 0.7999532054281703,
      "eval_runtime": 14.3233,
      "eval_samples_per_second": 475.451,
      "eval_steps_per_second": 59.484,
      "step": 1623
    },
    {
      "epoch": 3.6968576709796674,
      "grad_norm": 1.4018645286560059,
      "learning_rate": 3.1515711645101665e-05,
      "loss": 0.0764,
      "step": 2000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8398602166778805,
      "eval_f1": 0.42338430558177587,
      "eval_loss": 0.7413247227668762,
      "eval_precision": 0.2895756219333735,
      "eval_recall": 0.7870846981750117,
      "eval_runtime": 14.5396,
      "eval_samples_per_second": 468.375,
      "eval_steps_per_second": 58.598,
      "step": 2164
    },
    {
      "epoch": 4.621072088724584,
      "grad_norm": 1.0904265642166138,
      "learning_rate": 2.6894639556377083e-05,
      "loss": 0.0567,
      "step": 2500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8564886649182308,
      "eval_f1": 0.45455732567249935,
      "eval_loss": 0.7005925178527832,
      "eval_precision": 0.3152508603513856,
      "eval_recall": 0.8144595226953674,
      "eval_runtime": 14.2723,
      "eval_samples_per_second": 477.148,
      "eval_steps_per_second": 59.696,
      "step": 2705
    },
    {
      "epoch": 5.545286506469501,
      "grad_norm": 1.240962028503418,
      "learning_rate": 2.2273567467652497e-05,
      "loss": 0.0428,
      "step": 3000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8504057561069384,
      "eval_f1": 0.44700636942675154,
      "eval_loss": 0.8111857175827026,
      "eval_precision": 0.30710659898477155,
      "eval_recall": 0.8210107627515209,
      "eval_runtime": 14.3991,
      "eval_samples_per_second": 472.946,
      "eval_steps_per_second": 59.17,
      "step": 3246
    },
    {
      "epoch": 6.469500924214418,
      "grad_norm": 0.44737720489501953,
      "learning_rate": 1.7652495378927914e-05,
      "loss": 0.0332,
      "step": 3500
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8532961676301372,
      "eval_f1": 0.4493518337567586,
      "eval_loss": 0.904643714427948,
      "eval_precision": 0.3113658932924077,
      "eval_recall": 0.8069723912026205,
      "eval_runtime": 14.3036,
      "eval_samples_per_second": 476.105,
      "eval_steps_per_second": 59.566,
      "step": 3787
    },
    {
      "epoch": 7.393715341959335,
      "grad_norm": 0.7116318941116333,
      "learning_rate": 1.3031423290203328e-05,
      "loss": 0.0257,
      "step": 4000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8481538440413583,
      "eval_f1": 0.44435897435897437,
      "eval_loss": 0.9722912907600403,
      "eval_precision": 0.30602154335158044,
      "eval_recall": 0.8109499298081423,
      "eval_runtime": 14.4222,
      "eval_samples_per_second": 472.19,
      "eval_steps_per_second": 59.076,
      "step": 4328
    },
    {
      "epoch": 8.317929759704251,
      "grad_norm": 0.9520462155342102,
      "learning_rate": 8.410351201478742e-06,
      "loss": 0.022,
      "step": 4500
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.850186057368833,
      "eval_f1": 0.44668737060041414,
      "eval_loss": 1.002764105796814,
      "eval_precision": 0.30871042747272404,
      "eval_recall": 0.8076743097800655,
      "eval_runtime": 14.2485,
      "eval_samples_per_second": 477.944,
      "eval_steps_per_second": 59.796,
      "step": 4869
    },
    {
      "epoch": 9.242144177449168,
      "grad_norm": 0.6707109212875366,
      "learning_rate": 3.789279112754159e-06,
      "loss": 0.0181,
      "step": 5000
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.8533304955579661,
      "eval_f1": 0.45038613797131544,
      "eval_loss": 1.0022608041763306,
      "eval_precision": 0.31162999550965426,
      "eval_recall": 0.8118858212447356,
      "eval_runtime": 14.4559,
      "eval_samples_per_second": 471.089,
      "eval_steps_per_second": 58.938,
      "step": 5410
    },
    {
      "epoch": 10.0,
      "step": 5410,
      "total_flos": 1.7176580067661056e+16,
      "train_loss": 0.0812657987344287,
      "train_runtime": 1549.44,
      "train_samples_per_second": 223.332,
      "train_steps_per_second": 3.492
    }
  ],
  "logging_steps": 500,
  "max_steps": 5410,
  "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": 1.7176580067661056e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}