ner_lora_output

This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.1698
• Ank Name: {'precision': 0.6426229508196721, 'recall': 0.1694036300777874, 'f1': 0.26812585499316005, 'number': 1157}
• Ate: {'precision': 0.08817204301075268, 'recall': 0.2789115646258503, 'f1': 0.13398692810457516, 'number': 147}
• Ccount Number: {'precision': 0.05, 'recall': 0.024390243902439025, 'f1': 0.03278688524590164, 'number': 123}
• Ddress: {'precision': 0.13318284424379231, 'recall': 0.4306569343065693, 'f1': 0.20344827586206896, 'number': 137}
• Egree: {'precision': 0.12087912087912088, 'recall': 0.6149068322981367, 'f1': 0.20204081632653062, 'number': 161}
• Erson: {'precision': 0.025510204081632654, 'recall': 0.038461538461538464, 'f1': 0.030674846625766874, 'number': 130}
• Hone Number: {'precision': 0.06790123456790123, 'recall': 0.1864406779661017, 'f1': 0.09954751131221717, 'number': 177}
• Ity: {'precision': 0.022556390977443608, 'recall': 0.022222222222222223, 'f1': 0.022388059701492536, 'number': 135}
• Mail: {'precision': 0.4382855301321302, 'recall': 0.9477351916376306, 'f1': 0.5993829881004847, 'number': 1435}
• Niversity: {'precision': 0.042682926829268296, 'recall': 0.05384615384615385, 'f1': 0.047619047619047616, 'number': 130}
• Obby: {'precision': 0.028985507246376812, 'recall': 0.015267175572519083, 'f1': 0.019999999999999997, 'number': 131}
• Ob Title: {'precision': 0.008547008547008548, 'recall': 0.020833333333333332, 'f1': 0.012121212121212121, 'number': 144}
• Ostal Code: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 139}
• Ountry: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 92}
• Raduation Year: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 128}
• Redit Card Number: {'precision': 0.08717310087173101, 'recall': 0.4166666666666667, 'f1': 0.14418125643666324, 'number': 168}
• Sn: {'precision': 0.430939226519337, 'recall': 0.06372549019607843, 'f1': 0.11103202846975088, 'number': 1224}
• Tate: {'precision': 0.25925925925925924, 'recall': 0.00903225806451613, 'f1': 0.01745635910224439, 'number': 775}
• Vv: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 146}
• Xpiration Date: {'precision': 0.8, 'recall': 0.07920792079207921, 'f1': 0.14414414414414414, 'number': 808}
• Overall Precision: 0.2630
• Overall Recall: 0.2711
• Overall F1: 0.2670
• Overall Accuracy: 0.4303

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Ank Name	Ate	Ccount Number	Ddress	Egree	Erson	Hone Number	Ity	Mail	Niversity	Obby	Ob Title	Ostal Code	Ountry	Raduation Year	Redit Card Number	Sn	Tate	Vv	Xpiration Date	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
2.883	1.0	500	2.8381	{'precision': 0.14285714285714285, 'recall': 0.000864304235090752, 'f1': 0.0017182130584192437, 'number': 1157}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 147}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 123}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 137}	{'precision': 0.007855459544383346, 'recall': 0.12422360248447205, 'f1': 0.014776505356483192, 'number': 161}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 130}	{'precision': 0.0045193097781429745, 'recall': 0.062146892655367235, 'f1': 0.008425890463423976, 'number': 177}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 135}	{'precision': 0.2929440389294404, 'recall': 0.4195121951219512, 'f1': 0.3449856733524355, 'number': 1435}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 130}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 131}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 144}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 139}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 92}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 128}	{'precision': 0.0044943820224719105, 'recall': 0.07142857142857142, 'f1': 0.008456659619450317, 'number': 168}	{'precision': 0.18518518518518517, 'recall': 0.004084967320261438, 'f1': 0.007993605115907274, 'number': 1224}	{'precision': 0.5, 'recall': 0.0012903225806451613, 'f1': 0.002574002574002574, 'number': 775}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 146}	{'precision': 0.6956521739130435, 'recall': 0.019801980198019802, 'f1': 0.03850782190132371, 'number': 808}	0.0611	0.0892	0.0725	0.1993
2.5253	2.0	1000	2.3928	{'precision': 0.49382716049382713, 'recall': 0.03457216940363008, 'f1': 0.06462035541195477, 'number': 1157}	{'precision': 0.04771784232365145, 'recall': 0.1564625850340136, 'f1': 0.07313195548489666, 'number': 147}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 123}	{'precision': 0.1001890359168242, 'recall': 0.38686131386861317, 'f1': 0.15915915915915915, 'number': 137}	{'precision': 0.08584905660377358, 'recall': 0.5652173913043478, 'f1': 0.14905814905814904, 'number': 161}	{'precision': 0.011764705882352941, 'recall': 0.015384615384615385, 'f1': 0.013333333333333332, 'number': 130}	{'precision': 0.040268456375838924, 'recall': 0.1694915254237288, 'f1': 0.0650759219088937, 'number': 177}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 135}	{'precision': 0.3897707231040564, 'recall': 0.9240418118466899, 'f1': 0.5482737233822617, 'number': 1435}	{'precision': 0.017699115044247787, 'recall': 0.015384615384615385, 'f1': 0.01646090534979424, 'number': 130}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 131}	{'precision': 0.004016064257028112, 'recall': 0.006944444444444444, 'f1': 0.0050890585241730275, 'number': 144}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 139}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 92}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 128}	{'precision': 0.06563354603463993, 'recall': 0.42857142857142855, 'f1': 0.11383399209486166, 'number': 168}	{'precision': 0.23577235772357724, 'recall': 0.02369281045751634, 'f1': 0.04305864884929473, 'number': 1224}	{'precision': 0.14285714285714285, 'recall': 0.0012903225806451613, 'f1': 0.0025575447570332483, 'number': 775}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 146}	{'precision': 0.65, 'recall': 0.03217821782178218, 'f1': 0.06132075471698113, 'number': 808}	0.2061	0.2265	0.2158	0.3542
2.2675	3.0	1500	2.1698	{'precision': 0.6426229508196721, 'recall': 0.1694036300777874, 'f1': 0.26812585499316005, 'number': 1157}	{'precision': 0.08817204301075268, 'recall': 0.2789115646258503, 'f1': 0.13398692810457516, 'number': 147}	{'precision': 0.05, 'recall': 0.024390243902439025, 'f1': 0.03278688524590164, 'number': 123}	{'precision': 0.13318284424379231, 'recall': 0.4306569343065693, 'f1': 0.20344827586206896, 'number': 137}	{'precision': 0.12087912087912088, 'recall': 0.6149068322981367, 'f1': 0.20204081632653062, 'number': 161}	{'precision': 0.025510204081632654, 'recall': 0.038461538461538464, 'f1': 0.030674846625766874, 'number': 130}	{'precision': 0.06790123456790123, 'recall': 0.1864406779661017, 'f1': 0.09954751131221717, 'number': 177}	{'precision': 0.022556390977443608, 'recall': 0.022222222222222223, 'f1': 0.022388059701492536, 'number': 135}	{'precision': 0.4382855301321302, 'recall': 0.9477351916376306, 'f1': 0.5993829881004847, 'number': 1435}	{'precision': 0.042682926829268296, 'recall': 0.05384615384615385, 'f1': 0.047619047619047616, 'number': 130}	{'precision': 0.028985507246376812, 'recall': 0.015267175572519083, 'f1': 0.019999999999999997, 'number': 131}	{'precision': 0.008547008547008548, 'recall': 0.020833333333333332, 'f1': 0.012121212121212121, 'number': 144}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 139}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 92}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 128}	{'precision': 0.08717310087173101, 'recall': 0.4166666666666667, 'f1': 0.14418125643666324, 'number': 168}	{'precision': 0.430939226519337, 'recall': 0.06372549019607843, 'f1': 0.11103202846975088, 'number': 1224}	{'precision': 0.25925925925925924, 'recall': 0.00903225806451613, 'f1': 0.01745635910224439, 'number': 775}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 146}	{'precision': 0.8, 'recall': 0.07920792079207921, 'f1': 0.14414414414414414, 'number': 808}	0.2630	0.2711	0.2670	0.4303

Framework versions

• PEFT 0.13.2
• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.20.3