Loss: 0.6190
Precision: 0.5905
Recall: 0.4761
F1: 0.5272
Accuracy: 0.9246
By Entity: {'corporation': {'precision': 0.2571428571428571, 'recall': 0.2647058823529412, 'f1': 0.2608695652173913, 'number': 34}, 'creative-work': {'precision': 0.28169014084507044, 'recall': 0.19047619047619047, 'f1': 0.2272727272727273, 'number': 105}, 'group': {'precision': 0.16666666666666666, 'recall': 0.1794871794871795, 'f1': 0.1728395061728395, 'number': 39}, 'location': {'precision': 0.6376811594202898, 'recall': 0.5945945945945946, 'f1': 0.6153846153846154, 'number': 74}, 'person': {'precision': 0.7621621621621621, 'recall': 0.6, 'f1': 0.6714285714285715, 'number': 470}, 'product': {'precision': 0.41379310344827586, 'recall': 0.3157894736842105, 'f1': 0.3582089552238805, 'number': 114}}

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy	By Entity
No log	1.0	425	0.3552	0.5638	0.4438	0.4967	0.9217	{'corporation': {'precision': 0.1774193548387097, 'recall': 0.3235294117647059, 'f1': 0.22916666666666666, 'number': 34}, 'creative-work': {'precision': 0.3064516129032258, 'recall': 0.18095238095238095, 'f1': 0.22754491017964074, 'number': 105}, 'group': {'precision': 0.1702127659574468, 'recall': 0.20512820512820512, 'f1': 0.18604651162790697, 'number': 39}, 'location': {'precision': 0.6721311475409836, 'recall': 0.5540540540540541, 'f1': 0.6074074074074074, 'number': 74}, 'person': {'precision': 0.7854984894259819, 'recall': 0.5531914893617021, 'f1': 0.6491885143570537, 'number': 470}, 'product': {'precision': 0.3368421052631579, 'recall': 0.2807017543859649, 'f1': 0.30622009569377995, 'number': 114}}
0.059	2.0	850	0.5116	0.6066	0.4390	0.5094	0.9215	{'corporation': {'precision': 0.28, 'recall': 0.20588235294117646, 'f1': 0.23728813559322035, 'number': 34}, 'creative-work': {'precision': 0.37777777777777777, 'recall': 0.1619047619047619, 'f1': 0.22666666666666668, 'number': 105}, 'group': {'precision': 0.21052631578947367, 'recall': 0.3076923076923077, 'f1': 0.25, 'number': 39}, 'location': {'precision': 0.5797101449275363, 'recall': 0.5405405405405406, 'f1': 0.5594405594405595, 'number': 74}, 'person': {'precision': 0.7630057803468208, 'recall': 0.5617021276595745, 'f1': 0.6470588235294118, 'number': 470}, 'product': {'precision': 0.42857142857142855, 'recall': 0.23684210526315788, 'f1': 0.30508474576271183, 'number': 114}}
0.0314	3.0	1275	0.4661	0.5603	0.4725	0.5127	0.9255	{'corporation': {'precision': 0.1568627450980392, 'recall': 0.23529411764705882, 'f1': 0.18823529411764706, 'number': 34}, 'creative-work': {'precision': 0.28378378378378377, 'recall': 0.2, 'f1': 0.2346368715083799, 'number': 105}, 'group': {'precision': 0.1724137931034483, 'recall': 0.2564102564102564, 'f1': 0.2061855670103093, 'number': 39}, 'location': {'precision': 0.581081081081081, 'recall': 0.581081081081081, 'f1': 0.581081081081081, 'number': 74}, 'person': {'precision': 0.7486772486772487, 'recall': 0.6021276595744681, 'f1': 0.6674528301886793, 'number': 470}, 'product': {'precision': 0.42857142857142855, 'recall': 0.2631578947368421, 'f1': 0.32608695652173914, 'number': 114}}
0.0217	4.0	1700	0.5512	0.5850	0.4486	0.5078	0.9237	{'corporation': {'precision': 0.16666666666666666, 'recall': 0.23529411764705882, 'f1': 0.19512195121951217, 'number': 34}, 'creative-work': {'precision': 0.3333333333333333, 'recall': 0.23809523809523808, 'f1': 0.2777777777777778, 'number': 105}, 'group': {'precision': 0.11864406779661017, 'recall': 0.1794871794871795, 'f1': 0.14285714285714288, 'number': 39}, 'location': {'precision': 0.6779661016949152, 'recall': 0.5405405405405406, 'f1': 0.6015037593984962, 'number': 74}, 'person': {'precision': 0.8130841121495327, 'recall': 0.5553191489361702, 'f1': 0.6599241466498104, 'number': 470}, 'product': {'precision': 0.43037974683544306, 'recall': 0.2982456140350877, 'f1': 0.35233160621761656, 'number': 114}}
0.0106	5.0	2125	0.5409	0.5722	0.4928	0.5296	0.9238	{'corporation': {'precision': 0.25, 'recall': 0.29411764705882354, 'f1': 0.27027027027027023, 'number': 34}, 'creative-work': {'precision': 0.3225806451612903, 'recall': 0.19047619047619047, 'f1': 0.23952095808383234, 'number': 105}, 'group': {'precision': 0.18181818181818182, 'recall': 0.20512820512820512, 'f1': 0.1927710843373494, 'number': 39}, 'location': {'precision': 0.5529411764705883, 'recall': 0.6351351351351351, 'f1': 0.5911949685534591, 'number': 74}, 'person': {'precision': 0.7461139896373057, 'recall': 0.6127659574468085, 'f1': 0.6728971962616822, 'number': 470}, 'product': {'precision': 0.3786407766990291, 'recall': 0.34210526315789475, 'f1': 0.359447004608295, 'number': 114}}
0.0066	6.0	2550	0.5211	0.5758	0.4952	0.5325	0.9262	{'corporation': {'precision': 0.25, 'recall': 0.2647058823529412, 'f1': 0.2571428571428572, 'number': 34}, 'creative-work': {'precision': 0.32, 'recall': 0.22857142857142856, 'f1': 0.26666666666666666, 'number': 105}, 'group': {'precision': 0.19148936170212766, 'recall': 0.23076923076923078, 'f1': 0.20930232558139536, 'number': 39}, 'location': {'precision': 0.6, 'recall': 0.6081081081081081, 'f1': 0.6040268456375839, 'number': 74}, 'person': {'precision': 0.7306733167082294, 'recall': 0.6234042553191489, 'f1': 0.6727898966704936, 'number': 470}, 'product': {'precision': 0.4, 'recall': 0.2982456140350877, 'f1': 0.3417085427135679, 'number': 114}}
0.0066	7.0	2975	0.5475	0.5578	0.4904	0.5220	0.9234	{'corporation': {'precision': 0.1746031746031746, 'recall': 0.3235294117647059, 'f1': 0.2268041237113402, 'number': 34}, 'creative-work': {'precision': 0.3026315789473684, 'recall': 0.21904761904761905, 'f1': 0.25414364640883974, 'number': 105}, 'group': {'precision': 0.15384615384615385, 'recall': 0.20512820512820512, 'f1': 0.17582417582417584, 'number': 39}, 'location': {'precision': 0.5584415584415584, 'recall': 0.581081081081081, 'f1': 0.5695364238410595, 'number': 74}, 'person': {'precision': 0.7692307692307693, 'recall': 0.6170212765957447, 'f1': 0.6847697756788667, 'number': 470}, 'product': {'precision': 0.3888888888888889, 'recall': 0.30701754385964913, 'f1': 0.3431372549019608, 'number': 114}}
0.005	8.0	3400	0.5932	0.5602	0.4785	0.5161	0.9236	{'corporation': {'precision': 0.1836734693877551, 'recall': 0.2647058823529412, 'f1': 0.21686746987951805, 'number': 34}, 'creative-work': {'precision': 0.3246753246753247, 'recall': 0.23809523809523808, 'f1': 0.2747252747252747, 'number': 105}, 'group': {'precision': 0.12727272727272726, 'recall': 0.1794871794871795, 'f1': 0.14893617021276595, 'number': 39}, 'location': {'precision': 0.5714285714285714, 'recall': 0.5945945945945946, 'f1': 0.5827814569536424, 'number': 74}, 'person': {'precision': 0.7540106951871658, 'recall': 0.6, 'f1': 0.6682464454976303, 'number': 470}, 'product': {'precision': 0.4024390243902439, 'recall': 0.2894736842105263, 'f1': 0.33673469387755106, 'number': 114}}
0.0026	9.0	3825	0.6037	0.5882	0.4868	0.5327	0.9253	{'corporation': {'precision': 0.2647058823529412, 'recall': 0.2647058823529412, 'f1': 0.2647058823529412, 'number': 34}, 'creative-work': {'precision': 0.2876712328767123, 'recall': 0.2, 'f1': 0.23595505617977527, 'number': 105}, 'group': {'precision': 0.15555555555555556, 'recall': 0.1794871794871795, 'f1': 0.16666666666666666, 'number': 39}, 'location': {'precision': 0.6376811594202898, 'recall': 0.5945945945945946, 'f1': 0.6153846153846154, 'number': 74}, 'person': {'precision': 0.7572559366754618, 'recall': 0.6106382978723405, 'f1': 0.6760895170789164, 'number': 470}, 'product': {'precision': 0.42391304347826086, 'recall': 0.34210526315789475, 'f1': 0.37864077669902907, 'number': 114}}
0.0029	10.0	4250	0.6190	0.5905	0.4761	0.5272	0.9246	{'corporation': {'precision': 0.2571428571428571, 'recall': 0.2647058823529412, 'f1': 0.2608695652173913, 'number': 34}, 'creative-work': {'precision': 0.28169014084507044, 'recall': 0.19047619047619047, 'f1': 0.2272727272727273, 'number': 105}, 'group': {'precision': 0.16666666666666666, 'recall': 0.1794871794871795, 'f1': 0.1728395061728395, 'number': 39}, 'location': {'precision': 0.6376811594202898, 'recall': 0.5945945945945946, 'f1': 0.6153846153846154, 'number': 74}, 'person': {'precision': 0.7621621621621621, 'recall': 0.6, 'f1': 0.6714285714285715, 'number': 470}, 'product': {'precision': 0.41379310344827586, 'recall': 0.3157894736842105, 'f1': 0.3582089552238805, 'number': 114}}

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1

FabianJennrich/bert-finetuned-ner

bert-finetuned-ner

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

FabianJennrich/
bert-finetuned-ner