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: 0.1879
- Loc: {'precision': 0.6144200626959248, 'recall': 0.5714285714285714, 'f1': 0.5921450151057402, 'number': 686}
- Misc: {'precision': 0.6759708737864077, 'recall': 0.6975579211020664, 'f1': 0.6865947611710324, 'number': 1597}
- Org: {'precision': 0.6231884057971014, 'recall': 0.6417910447761194, 'f1': 0.6323529411764706, 'number': 268}
- Per: {'precision': 0.6520963425512935, 'recall': 0.7567287784679089, 'f1': 0.7005270723526592, 'number': 966}
- Overall Precision: 0.6541
- Overall Recall: 0.6850
- Overall F1: 0.6692
- Overall Accuracy: 0.9400
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Er | Isc | Oc | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|---|---|---|---|---|---|---|---|---|---|---|
| 0.2687 | 1.0 | 654 | 0.2022 | {'precision': 0.6098294884653962, 'recall': 0.629399585921325, 'f1': 0.6194600101884871, 'number': 966} | {'precision': 0.6234604105571847, 'recall': 0.6656230432060113, 'f1': 0.6438522107813446, 'number': 1597} | {'precision': 0.5617792421746294, 'recall': 0.4970845481049563, 'f1': 0.5274555297757154, 'number': 686} | 0.6080 | 0.6193 | 0.6136 | 0.9325 |
| 0.1623 | 2.0 | 1308 | 0.1819 | {'precision': 0.6175523349436393, 'recall': 0.7939958592132506, 'f1': 0.6947463768115941, 'number': 966} | {'precision': 0.6879526003949967, 'recall': 0.654351909830933, 'f1': 0.6707317073170731, 'number': 1597} | {'precision': 0.6374367622259697, 'recall': 0.5510204081632653, 'f1': 0.5910867865519938, 'number': 686} | 0.6530 | 0.6741 | 0.6633 | 0.9390 |
| 0.128 | 3.0 | 1962 | 0.1879 | {'precision': 0.6520963425512935, 'recall': 0.7567287784679089, 'f1': 0.7005270723526592, 'number': 966} | {'precision': 0.6759708737864077, 'recall': 0.6975579211020664, 'f1': 0.6865947611710324, 'number': 1597} | {'precision': 0.6144200626959248, 'recall': 0.5714285714285714, 'f1': 0.5921450151057402, 'number': 686} | 0.6566 | 0.6885 | 0.6722 | 0.9400 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3