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: 0.1522
- Loc: {'precision': 0.7952488687782805, 'recall': 0.703, 'f1': 0.7462845010615711, 'number': 1000}
- Misc: {'precision': 0.6310931641188348, 'recall': 0.6640364188163884, 'f1': 0.6471458148476782, 'number': 3295}
- Org: {'precision': 0.6708074534161491, 'recall': 0.6792452830188679, 'f1': 0.6749999999999999, 'number': 477}
- Per: {'precision': 0.7778738115816768, 'recall': 0.7772020725388601, 'f1': 0.7775377969762419, 'number': 1158}
- Overall Precision: 0.6869
- Overall Recall: 0.6939
- Overall F1: 0.6904
- Overall Accuracy: 0.9567
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 | Loc | Misc | Org | Per | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.1195 | 1.0 | 2044 | 0.1425 | {'precision': 0.750620347394541, 'recall': 0.605, 'f1': 0.6699889258028793, 'number': 1000} | {'precision': 0.6498784300104203, 'recall': 0.5678300455235205, 'f1': 0.606090055069647, 'number': 3295} | {'precision': 0.6763392857142857, 'recall': 0.6352201257861635, 'f1': 0.6551351351351351, 'number': 477} | {'precision': 0.6595744680851063, 'recall': 0.7763385146804835, 'f1': 0.7132090440301467, 'number': 1158} | 0.6692 | 0.6202 | 0.6438 | 0.9511 |
| 0.0736 | 2.0 | 4088 | 0.1387 | {'precision': 0.7714604236343366, 'recall': 0.692, 'f1': 0.7295730100158145, 'number': 1000} | {'precision': 0.6479814115596864, 'recall': 0.6770864946889226, 'f1': 0.6622143069159989, 'number': 3295} | {'precision': 0.7018348623853211, 'recall': 0.6415094339622641, 'f1': 0.6703176341730558, 'number': 477} | {'precision': 0.7717484926787253, 'recall': 0.7737478411053541, 'f1': 0.7727468736524364, 'number': 1158} | 0.6948 | 0.6956 | 0.6952 | 0.9575 |
| 0.0499 | 3.0 | 6132 | 0.1522 | {'precision': 0.7952488687782805, 'recall': 0.703, 'f1': 0.7462845010615711, 'number': 1000} | {'precision': 0.6310931641188348, 'recall': 0.6640364188163884, 'f1': 0.6471458148476782, 'number': 3295} | {'precision': 0.6708074534161491, 'recall': 0.6792452830188679, 'f1': 0.6749999999999999, 'number': 477} | {'precision': 0.7778738115816768, 'recall': 0.7772020725388601, 'f1': 0.7775377969762419, 'number': 1158} | 0.6869 | 0.6939 | 0.6904 | 0.9567 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3