Data_extraction
This model is a fine-tuned version of SCUT-DLVCLab/lilt-roberta-en-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4277
- Fsc Code: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 22}
- Ame: {'precision': 0.391304347826087, 'recall': 0.42857142857142855, 'f1': 0.4090909090909091, 'number': 42}
- Ccount No: {'precision': 0.75, 'recall': 0.5, 'f1': 0.6, 'number': 6}
- Ign: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 5}
- Mount: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 13}
- Ther: {'precision': 0.5287356321839081, 'recall': 0.5348837209302325, 'f1': 0.5317919075144507, 'number': 86}
- Overall Precision: 0.6045
- Overall Recall: 0.6149
- Overall F1: 0.6097
- Overall Accuracy: 0.9431
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: 5e-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
- training_steps: 2500
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Fsc Code | Ame | Ccount No | Ign | Mount | Ther | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0.1559 | 20.0 | 200 | 0.2349 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 22} | {'precision': 0.3448275862068966, 'recall': 0.47619047619047616, 'f1': 0.39999999999999997, 'number': 42} | {'precision': 0.75, 'recall': 0.5, 'f1': 0.6, 'number': 6} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 5} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 13} | {'precision': 0.4329896907216495, 'recall': 0.4883720930232558, 'f1': 0.45901639344262296, 'number': 86} | 0.5155 | 0.5747 | 0.5435 | 0.9376 |
0.0138 | 40.0 | 400 | 0.2607 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 22} | {'precision': 0.3148148148148148, 'recall': 0.40476190476190477, 'f1': 0.3541666666666667, 'number': 42} | {'precision': 0.75, 'recall': 0.5, 'f1': 0.6, 'number': 6} | {'precision': 1.0, 'recall': 0.8, 'f1': 0.888888888888889, 'number': 5} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 13} | {'precision': 0.5, 'recall': 0.5465116279069767, 'f1': 0.5222222222222221, 'number': 86} | 0.5550 | 0.6092 | 0.5808 | 0.9372 |
0.0031 | 60.0 | 600 | 0.3808 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 22} | {'precision': 0.2786885245901639, 'recall': 0.40476190476190477, 'f1': 0.33009708737864074, 'number': 42} | {'precision': 1.0, 'recall': 0.6666666666666666, 'f1': 0.8, 'number': 6} | {'precision': 0.8333333333333334, 'recall': 1.0, 'f1': 0.9090909090909091, 'number': 5} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 13} | {'precision': 0.4077669902912621, 'recall': 0.4883720930232558, 'f1': 0.44444444444444436, 'number': 86} | 0.4928 | 0.5920 | 0.5379 | 0.9372 |
0.0031 | 80.0 | 800 | 0.3239 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 22} | {'precision': 0.2807017543859649, 'recall': 0.38095238095238093, 'f1': 0.32323232323232326, 'number': 42} | {'precision': 1.0, 'recall': 0.8333333333333334, 'f1': 0.9090909090909091, 'number': 6} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 5} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 13} | {'precision': 0.45, 'recall': 0.5232558139534884, 'f1': 0.48387096774193555, 'number': 86} | 0.5248 | 0.6092 | 0.5638 | 0.9532 |
0.0007 | 100.0 | 1000 | 0.3718 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 22} | {'precision': 0.375, 'recall': 0.42857142857142855, 'f1': 0.39999999999999997, 'number': 42} | {'precision': 0.6666666666666666, 'recall': 0.6666666666666666, 'f1': 0.6666666666666666, 'number': 6} | {'precision': 0.8333333333333334, 'recall': 1.0, 'f1': 0.9090909090909091, 'number': 5} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 13} | {'precision': 0.4891304347826087, 'recall': 0.5232558139534884, 'f1': 0.5056179775280899, 'number': 86} | 0.5722 | 0.6149 | 0.5928 | 0.9467 |
0.0002 | 120.0 | 1200 | 0.4208 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 22} | {'precision': 0.34, 'recall': 0.40476190476190477, 'f1': 0.36956521739130443, 'number': 42} | {'precision': 0.5, 'recall': 0.5, 'f1': 0.5, 'number': 6} | {'precision': 0.8333333333333334, 'recall': 1.0, 'f1': 0.9090909090909091, 'number': 5} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 13} | {'precision': 0.4731182795698925, 'recall': 0.5116279069767442, 'f1': 0.4916201117318436, 'number': 86} | 0.5474 | 0.5977 | 0.5714 | 0.9408 |
0.0003 | 140.0 | 1400 | 0.4155 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 22} | {'precision': 0.3333333333333333, 'recall': 0.40476190476190477, 'f1': 0.3655913978494623, 'number': 42} | {'precision': 0.8, 'recall': 0.6666666666666666, 'f1': 0.7272727272727272, 'number': 6} | {'precision': 0.8333333333333334, 'recall': 1.0, 'f1': 0.9090909090909091, 'number': 5} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 13} | {'precision': 0.46808510638297873, 'recall': 0.5116279069767442, 'f1': 0.4888888888888889, 'number': 86} | 0.5497 | 0.6034 | 0.5753 | 0.9397 |
0.0004 | 160.0 | 1600 | 0.4277 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 22} | {'precision': 0.391304347826087, 'recall': 0.42857142857142855, 'f1': 0.4090909090909091, 'number': 42} | {'precision': 0.75, 'recall': 0.5, 'f1': 0.6, 'number': 6} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 5} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 13} | {'precision': 0.5287356321839081, 'recall': 0.5348837209302325, 'f1': 0.5317919075144507, 'number': 86} | 0.6045 | 0.6149 | 0.6097 | 0.9431 |
0.0001 | 180.0 | 1800 | 0.3870 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 22} | {'precision': 0.27586206896551724, 'recall': 0.38095238095238093, 'f1': 0.32, 'number': 42} | {'precision': 0.75, 'recall': 0.5, 'f1': 0.6, 'number': 6} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 5} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 13} | {'precision': 0.45, 'recall': 0.5232558139534884, 'f1': 0.48387096774193555, 'number': 86} | 0.5149 | 0.5977 | 0.5532 | 0.9476 |
0.0001 | 200.0 | 2000 | 0.3956 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 22} | {'precision': 0.3617021276595745, 'recall': 0.40476190476190477, 'f1': 0.3820224719101123, 'number': 42} | {'precision': 0.75, 'recall': 0.5, 'f1': 0.6, 'number': 6} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 5} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 13} | {'precision': 0.5056179775280899, 'recall': 0.5232558139534884, 'f1': 0.5142857142857142, 'number': 86} | 0.5833 | 0.6034 | 0.5932 | 0.9526 |
0.0001 | 220.0 | 2200 | 0.4029 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 22} | {'precision': 0.3469387755102041, 'recall': 0.40476190476190477, 'f1': 0.3736263736263736, 'number': 42} | {'precision': 0.6, 'recall': 0.5, 'f1': 0.5454545454545454, 'number': 6} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 5} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 13} | {'precision': 0.5, 'recall': 0.5348837209302325, 'f1': 0.5168539325842696, 'number': 86} | 0.5699 | 0.6092 | 0.5889 | 0.9508 |
0.0 | 240.0 | 2400 | 0.4031 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 22} | {'precision': 0.34, 'recall': 0.40476190476190477, 'f1': 0.36956521739130443, 'number': 42} | {'precision': 0.75, 'recall': 0.5, 'f1': 0.6, 'number': 6} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 5} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 13} | {'precision': 0.4891304347826087, 'recall': 0.5232558139534884, 'f1': 0.5056179775280899, 'number': 86} | 0.5645 | 0.6034 | 0.5833 | 0.9499 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 6
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for indudesane/Data_extraction
Base model
SCUT-DLVCLab/lilt-roberta-en-base