{
  "best_metric": 0.9476082004555808,
  "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-4250",
  "epoch": 9.988249118683902,
  "eval_steps": 500,
  "global_step": 4250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9988249118683902,
      "eval_accuracy": 0.9982355445095912,
      "eval_f1": 0.9108726084927671,
      "eval_loss": 0.005039099138230085,
      "eval_precision": 0.9251184834123223,
      "eval_recall": 0.8970588235294118,
      "eval_runtime": 14.2012,
      "eval_samples_per_second": 479.538,
      "eval_steps_per_second": 59.995,
      "step": 425
    },
    {
      "epoch": 1.1750881316098707,
      "grad_norm": 0.14603009819984436,
      "learning_rate": 4.411764705882353e-05,
      "loss": 0.0196,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9987710601837231,
      "eval_f1": 0.9308584686774942,
      "eval_loss": 0.0038418550975620747,
      "eval_precision": 0.9400187441424555,
      "eval_recall": 0.921875,
      "eval_runtime": 14.3817,
      "eval_samples_per_second": 473.517,
      "eval_steps_per_second": 59.242,
      "step": 851
    },
    {
      "epoch": 2.3501762632197414,
      "grad_norm": 0.28499969840049744,
      "learning_rate": 3.8235294117647055e-05,
      "loss": 0.0031,
      "step": 1000
    },
    {
      "epoch": 2.99882491186839,
      "eval_accuracy": 0.9987779257692888,
      "eval_f1": 0.9313680331644403,
      "eval_loss": 0.0035449278075248003,
      "eval_precision": 0.9335180055401662,
      "eval_recall": 0.9292279411764706,
      "eval_runtime": 14.4856,
      "eval_samples_per_second": 470.122,
      "eval_steps_per_second": 58.817,
      "step": 1276
    },
    {
      "epoch": 3.525264394829612,
      "grad_norm": 0.0012828998733311892,
      "learning_rate": 3.235294117647059e-05,
      "loss": 0.0017,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9987641945981572,
      "eval_f1": 0.9355416293643687,
      "eval_loss": 0.004063209984451532,
      "eval_precision": 0.9118673647469459,
      "eval_recall": 0.9604779411764706,
      "eval_runtime": 14.5153,
      "eval_samples_per_second": 469.161,
      "eval_steps_per_second": 58.697,
      "step": 1702
    },
    {
      "epoch": 4.700352526439483,
      "grad_norm": 0.11785320192575455,
      "learning_rate": 2.647058823529412e-05,
      "loss": 0.0009,
      "step": 2000
    },
    {
      "epoch": 4.9988249118683905,
      "eval_accuracy": 0.9989495654084337,
      "eval_f1": 0.9456869009584664,
      "eval_loss": 0.004716179799288511,
      "eval_precision": 0.9392565729827742,
      "eval_recall": 0.9522058823529411,
      "eval_runtime": 14.4659,
      "eval_samples_per_second": 470.761,
      "eval_steps_per_second": 58.897,
      "step": 2127
    },
    {
      "epoch": 5.875440658049354,
      "grad_norm": 0.0034638349898159504,
      "learning_rate": 2.058823529411765e-05,
      "loss": 0.0004,
      "step": 2500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9989152374806047,
      "eval_f1": 0.9421487603305785,
      "eval_loss": 0.005501348990947008,
      "eval_precision": 0.9412844036697248,
      "eval_recall": 0.9430147058823529,
      "eval_runtime": 14.3237,
      "eval_samples_per_second": 475.435,
      "eval_steps_per_second": 59.482,
      "step": 2553
    },
    {
      "epoch": 6.9988249118683905,
      "eval_accuracy": 0.9989426998228679,
      "eval_f1": 0.9446962828649138,
      "eval_loss": 0.005442324560135603,
      "eval_precision": 0.9320214669051878,
      "eval_recall": 0.9577205882352942,
      "eval_runtime": 14.4857,
      "eval_samples_per_second": 470.12,
      "eval_steps_per_second": 58.817,
      "step": 2978
    },
    {
      "epoch": 7.050528789659224,
      "grad_norm": 0.0006337326485663652,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 0.0003,
      "step": 3000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9989358342373021,
      "eval_f1": 0.9469387755102041,
      "eval_loss": 0.005284155253320932,
      "eval_precision": 0.9346463742166518,
      "eval_recall": 0.9595588235294118,
      "eval_runtime": 14.3391,
      "eval_samples_per_second": 474.925,
      "eval_steps_per_second": 59.418,
      "step": 3404
    },
    {
      "epoch": 8.225616921269095,
      "grad_norm": 0.0004202235140837729,
      "learning_rate": 8.823529411764707e-06,
      "loss": 0.0002,
      "step": 3500
    },
    {
      "epoch": 8.99882491186839,
      "eval_accuracy": 0.9989221030661705,
      "eval_f1": 0.9457364341085271,
      "eval_loss": 0.005664878059178591,
      "eval_precision": 0.9384615384615385,
      "eval_recall": 0.953125,
      "eval_runtime": 14.3719,
      "eval_samples_per_second": 473.842,
      "eval_steps_per_second": 59.282,
      "step": 3829
    },
    {
      "epoch": 9.400705052878966,
      "grad_norm": 0.00056758540449664,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 0.0001,
      "step": 4000
    },
    {
      "epoch": 9.988249118683902,
      "eval_accuracy": 0.9989632965795653,
      "eval_f1": 0.9476082004555808,
      "eval_loss": 0.005463225767016411,
      "eval_precision": 0.9394760614272809,
      "eval_recall": 0.9558823529411765,
      "eval_runtime": 14.9618,
      "eval_samples_per_second": 455.159,
      "eval_steps_per_second": 56.945,
      "step": 4250
    },
    {
      "epoch": 9.988249118683902,
      "step": 4250,
      "total_flos": 1.2649124434987926e+16,
      "train_loss": 0.0030834444165229796,
      "train_runtime": 1203.605,
      "train_samples_per_second": 226.229,
      "train_steps_per_second": 3.531
    }
  ],
  "logging_steps": 500,
  "max_steps": 4250,
  "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": 1.2649124434987926e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}