metadata

license: mit
tags:
  - generated_from_trainer
model-index:
  - name: camembert-ner-finetuned-jul
    results: []

camembert-ner-finetuned-jul

This model is a fine-tuned version of Jean-Baptiste/camembert-ner on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1016
Loc: {'precision': 0.7560975609756098, 'recall': 0.7848101265822784, 'f1': 0.7701863354037267, 'number': 316}
Misc: {'precision': 0.5681818181818182, 'recall': 0.44642857142857145, 'f1': 0.5, 'number': 56}
Org: {'precision': 0.8184818481848185, 'recall': 0.8184818481848185, 'f1': 0.8184818481848186, 'number': 303}
Per: {'precision': 0.8456591639871383, 'recall': 0.8167701863354038, 'f1': 0.8309636650868879, 'number': 322}
Overall Precision: 0.7951
Overall Recall: 0.7864
Overall F1: 0.7907
Overall Accuracy: 0.9834

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: 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	Loc	Misc	Org	Per	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
No log	1.0	476	0.0747	{'precision': 0.6298342541436464, 'recall': 0.7215189873417721, 'f1': 0.672566371681416, 'number': 316}	{'precision': 0.6666666666666666, 'recall': 0.2857142857142857, 'f1': 0.4, 'number': 56}	{'precision': 0.6743515850144092, 'recall': 0.7722772277227723, 'f1': 0.7199999999999999, 'number': 303}	{'precision': 0.7070422535211267, 'recall': 0.7795031055900621, 'f1': 0.741506646971935, 'number': 322}	0.6700	0.7312	0.6993	0.9795
0.1172	2.0	952	0.0640	{'precision': 0.7471264367816092, 'recall': 0.8227848101265823, 'f1': 0.7831325301204819, 'number': 316}	{'precision': 0.6363636363636364, 'recall': 0.375, 'f1': 0.47191011235955066, 'number': 56}	{'precision': 0.7660256410256411, 'recall': 0.7887788778877888, 'f1': 0.7772357723577236, 'number': 303}	{'precision': 0.8138801261829653, 'recall': 0.8012422360248447, 'f1': 0.8075117370892019, 'number': 322}	0.7703	0.7803	0.7753	0.9839
0.0503	3.0	1428	0.0718	{'precision': 0.707774798927614, 'recall': 0.8354430379746836, 'f1': 0.7663280116110305, 'number': 316}	{'precision': 0.75, 'recall': 0.42857142857142855, 'f1': 0.5454545454545454, 'number': 56}	{'precision': 0.7639751552795031, 'recall': 0.8118811881188119, 'f1': 0.7872, 'number': 303}	{'precision': 0.8024316109422492, 'recall': 0.8198757763975155, 'f1': 0.8110599078341013, 'number': 322}	0.7557	0.8004	0.7774	0.9831
0.0273	4.0	1904	0.0859	{'precision': 0.7601246105919003, 'recall': 0.7721518987341772, 'f1': 0.7660910518053375, 'number': 316}	{'precision': 0.5897435897435898, 'recall': 0.4107142857142857, 'f1': 0.4842105263157895, 'number': 56}	{'precision': 0.75, 'recall': 0.8514851485148515, 'f1': 0.7975270479134468, 'number': 303}	{'precision': 0.8178913738019169, 'recall': 0.7950310559006211, 'f1': 0.8062992125984252, 'number': 322}	0.7679	0.7834	0.7756	0.9823
0.0179	5.0	2380	0.0924	{'precision': 0.7652733118971061, 'recall': 0.7531645569620253, 'f1': 0.759170653907496, 'number': 316}	{'precision': 0.575, 'recall': 0.4107142857142857, 'f1': 0.47916666666666663, 'number': 56}	{'precision': 0.8116883116883117, 'recall': 0.8250825082508251, 'f1': 0.8183306055646481, 'number': 303}	{'precision': 0.8264984227129337, 'recall': 0.8136645962732919, 'f1': 0.8200312989045383, 'number': 322}	0.7920	0.7753	0.7836	0.9834
0.0126	6.0	2856	0.0881	{'precision': 0.7197640117994101, 'recall': 0.7721518987341772, 'f1': 0.7450381679389314, 'number': 316}	{'precision': 0.5333333333333333, 'recall': 0.42857142857142855, 'f1': 0.4752475247524753, 'number': 56}	{'precision': 0.8245033112582781, 'recall': 0.8217821782178217, 'f1': 0.8231404958677686, 'number': 303}	{'precision': 0.8096676737160121, 'recall': 0.8322981366459627, 'f1': 0.8208269525267994, 'number': 322}	0.7719	0.7874	0.7795	0.9830
0.0094	7.0	3332	0.0988	{'precision': 0.7570977917981072, 'recall': 0.759493670886076, 'f1': 0.7582938388625592, 'number': 316}	{'precision': 0.575, 'recall': 0.4107142857142857, 'f1': 0.47916666666666663, 'number': 56}	{'precision': 0.8305647840531561, 'recall': 0.8250825082508251, 'f1': 0.8278145695364238, 'number': 303}	{'precision': 0.8213166144200627, 'recall': 0.8136645962732919, 'f1': 0.8174726989079563, 'number': 322}	0.7932	0.7773	0.7852	0.9833
0.0057	8.0	3808	0.1023	{'precision': 0.7704402515723271, 'recall': 0.7753164556962026, 'f1': 0.7728706624605678, 'number': 316}	{'precision': 0.6153846153846154, 'recall': 0.42857142857142855, 'f1': 0.5052631578947369, 'number': 56}	{'precision': 0.8283828382838284, 'recall': 0.8283828382838284, 'f1': 0.8283828382838284, 'number': 303}	{'precision': 0.8436482084690554, 'recall': 0.8043478260869565, 'f1': 0.8235294117647061, 'number': 322}	0.8056	0.7813	0.7933	0.9838
0.0058	9.0	4284	0.1005	{'precision': 0.7584097859327217, 'recall': 0.7848101265822784, 'f1': 0.7713841368584758, 'number': 316}	{'precision': 0.5555555555555556, 'recall': 0.44642857142857145, 'f1': 0.4950495049504951, 'number': 56}	{'precision': 0.8239202657807309, 'recall': 0.8184818481848185, 'f1': 0.8211920529801325, 'number': 303}	{'precision': 0.8538961038961039, 'recall': 0.8167701863354038, 'f1': 0.834920634920635, 'number': 322}	0.7992	0.7864	0.7927	0.9836
0.0045	10.0	4760	0.1016	{'precision': 0.7560975609756098, 'recall': 0.7848101265822784, 'f1': 0.7701863354037267, 'number': 316}	{'precision': 0.5681818181818182, 'recall': 0.44642857142857145, 'f1': 0.5, 'number': 56}	{'precision': 0.8184818481848185, 'recall': 0.8184818481848185, 'f1': 0.8184818481848186, 'number': 303}	{'precision': 0.8456591639871383, 'recall': 0.8167701863354038, 'f1': 0.8309636650868879, 'number': 322}	0.7951	0.7864	0.7907	0.9834

Framework versions

Transformers 4.29.1
Pytorch 2.0.0+cu118
Datasets 2.12.0
Tokenizers 0.13.3