RoBERTa_Combined_Generated_v2_2000_Fold5

This model is a fine-tuned version of ICT2214Team7/RoBERTa_Test_Training on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0438
• Precision: 0.8787
• Recall: 0.9432
• F1: 0.9098
• Accuracy: 0.9869
• Report: {'AGE': {'precision': 0.9727272727272728, 'recall': 0.9907407407407407, 'f1-score': 0.981651376146789, 'support': 108}, 'LOC': {'precision': 0.7784810126582279, 'recall': 0.924812030075188, 'f1-score': 0.845360824742268, 'support': 266}, 'NAT': {'precision': 0.8813559322033898, 'recall': 0.9570552147239264, 'f1-score': 0.9176470588235294, 'support': 163}, 'ORG': {'precision': 0.9379310344827586, 'recall': 0.912751677852349, 'f1-score': 0.9251700680272109, 'support': 149}, 'PER': {'precision': 0.9559748427672956, 'recall': 0.9559748427672956, 'f1-score': 0.9559748427672956, 'support': 159}, 'micro avg': {'precision': 0.8787210584343991, 'recall': 0.9431952662721893, 'f1-score': 0.9098173515981735, 'support': 845}, 'macro avg': {'precision': 0.9052940189677889, 'recall': 0.9482669012319, 'f1-score': 0.9251608341014187, 'support': 845}, 'weighted avg': {'precision': 0.8846665513712635, 'recall': 0.9431952662721893, 'f1-score': 0.9116108150645991, 'support': 845}}

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
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy	Report
No log	1.0	160	0.0554	0.8542	0.9361	0.8933	0.9826	{'AGE': {'precision': 0.9727272727272728, 'recall': 0.9907407407407407, 'f1-score': 0.981651376146789, 'support': 108}, 'LOC': {'precision': 0.7591463414634146, 'recall': 0.9360902255639098, 'f1-score': 0.8383838383838383, 'support': 266}, 'NAT': {'precision': 0.8579234972677595, 'recall': 0.9631901840490797, 'f1-score': 0.907514450867052, 'support': 163}, 'ORG': {'precision': 0.8904109589041096, 'recall': 0.87248322147651, 'f1-score': 0.8813559322033899, 'support': 149}, 'PER': {'precision': 0.9308176100628931, 'recall': 0.9308176100628931, 'f1-score': 0.9308176100628931, 'support': 159}, 'micro avg': {'precision': 0.8542116630669546, 'recall': 0.936094674556213, 'f1-score': 0.8932806324110671, 'support': 845}, 'macro avg': {'precision': 0.88220513608509, 'recall': 0.9386643963786266, 'f1-score': 0.9079446415327924, 'support': 845}, 'weighted avg': {'precision': 0.8609470239232793, 'recall': 0.936094674556213, 'f1-score': 0.8950004012113477, 'support': 845}}
No log	2.0	320	0.0414	0.8776	0.9337	0.9048	0.9863	{'AGE': {'precision': 0.9727272727272728, 'recall': 0.9907407407407407, 'f1-score': 0.981651376146789, 'support': 108}, 'LOC': {'precision': 0.7672955974842768, 'recall': 0.9172932330827067, 'f1-score': 0.8356164383561644, 'support': 266}, 'NAT': {'precision': 0.8953488372093024, 'recall': 0.9447852760736196, 'f1-score': 0.9194029850746268, 'support': 163}, 'ORG': {'precision': 0.9241379310344827, 'recall': 0.8993288590604027, 'f1-score': 0.9115646258503401, 'support': 149}, 'PER': {'precision': 0.974025974025974, 'recall': 0.9433962264150944, 'f1-score': 0.9584664536741214, 'support': 159}, 'micro avg': {'precision': 0.8776418242491657, 'recall': 0.9337278106508876, 'f1-score': 0.9048165137614678, 'support': 845}, 'macro avg': {'precision': 0.9067071224962617, 'recall': 0.9391088670745129, 'f1-score': 0.9213403758204084, 'support': 845}, 'weighted avg': {'precision': 0.8848091318872748, 'recall': 0.9337278106508876, 'f1-score': 0.906951838082418, 'support': 845}}
No log	3.0	480	0.0438	0.8787	0.9432	0.9098	0.9869	{'AGE': {'precision': 0.9727272727272728, 'recall': 0.9907407407407407, 'f1-score': 0.981651376146789, 'support': 108}, 'LOC': {'precision': 0.7784810126582279, 'recall': 0.924812030075188, 'f1-score': 0.845360824742268, 'support': 266}, 'NAT': {'precision': 0.8813559322033898, 'recall': 0.9570552147239264, 'f1-score': 0.9176470588235294, 'support': 163}, 'ORG': {'precision': 0.9379310344827586, 'recall': 0.912751677852349, 'f1-score': 0.9251700680272109, 'support': 149}, 'PER': {'precision': 0.9559748427672956, 'recall': 0.9559748427672956, 'f1-score': 0.9559748427672956, 'support': 159}, 'micro avg': {'precision': 0.8787210584343991, 'recall': 0.9431952662721893, 'f1-score': 0.9098173515981735, 'support': 845}, 'macro avg': {'precision': 0.9052940189677889, 'recall': 0.9482669012319, 'f1-score': 0.9251608341014187, 'support': 845}, 'weighted avg': {'precision': 0.8846665513712635, 'recall': 0.9431952662721893, 'f1-score': 0.9116108150645991, 'support': 845}}

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1