RoBERTa_Combined_Generated_v2_2000_Fold4

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: 0.0526
• Precision: 0.8689
• Recall: 0.9276
• F1: 0.8973
• Accuracy: 0.9856
• Report: {'AGE': {'precision': 0.9469026548672567, 'recall': 1.0, 'f1-score': 0.9727272727272728, 'support': 107}, 'LOC': {'precision': 0.7831325301204819, 'recall': 0.9090909090909091, 'f1-score': 0.8414239482200647, 'support': 286}, 'NAT': {'precision': 0.9096774193548387, 'recall': 0.9657534246575342, 'f1-score': 0.93687707641196, 'support': 146}, 'ORG': {'precision': 0.8943661971830986, 'recall': 0.8639455782312925, 'f1-score': 0.8788927335640138, 'support': 147}, 'PER': {'precision': 0.930379746835443, 'recall': 0.9363057324840764, 'f1-score': 0.9333333333333332, 'support': 157}, 'micro avg': {'precision': 0.8688888888888889, 'recall': 0.9276393831553974, 'f1-score': 0.8973034997131383, 'support': 843}, 'macro avg': {'precision': 0.8928917096722238, 'recall': 0.9350191288927625, 'f1-score': 0.912650872851329, 'support': 843}, 'weighted avg': {'precision': 0.872655803262326, 'recall': 0.9276393831553974, 'f1-score': 0.8982724622730086, 'support': 843}}

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	0.0509	0.8521	0.9229	0.8861	0.9840	{'AGE': {'precision': 0.963963963963964, 'recall': 1.0, 'f1-score': 0.9816513761467891, 'support': 107}, 'LOC': {'precision': 0.7602339181286549, 'recall': 0.9090909090909091, 'f1-score': 0.8280254777070064, 'support': 286}, 'NAT': {'precision': 0.875, 'recall': 0.958904109589041, 'f1-score': 0.9150326797385621, 'support': 146}, 'ORG': {'precision': 0.8936170212765957, 'recall': 0.8571428571428571, 'f1-score': 0.875, 'support': 147}, 'PER': {'precision': 0.9119496855345912, 'recall': 0.9235668789808917, 'f1-score': 0.9177215189873418, 'support': 157}, 'micro avg': {'precision': 0.8521358159912377, 'recall': 0.9228944246737841, 'f1-score': 0.8861047835990888, 'support': 843}, 'macro avg': {'precision': 0.8809529177807611, 'recall': 0.9297409509607398, 'f1-score': 0.9034862105159398, 'support': 843}, 'weighted avg': {'precision': 0.8574838048464174, 'recall': 0.9228944246737841, 'f1-score': 0.8874899568146536, 'support': 843}}
No log	2.0	320	0.0581	0.8673	0.9383	0.9014	0.9842	{'AGE': {'precision': 0.9469026548672567, 'recall': 1.0, 'f1-score': 0.9727272727272728, 'support': 107}, 'LOC': {'precision': 0.7922848664688428, 'recall': 0.9335664335664335, 'f1-score': 0.8571428571428572, 'support': 286}, 'NAT': {'precision': 0.9038461538461539, 'recall': 0.9657534246575342, 'f1-score': 0.9337748344370861, 'support': 146}, 'ORG': {'precision': 0.8698630136986302, 'recall': 0.8639455782312925, 'f1-score': 0.8668941979522184, 'support': 147}, 'PER': {'precision': 0.93125, 'recall': 0.9490445859872612, 'f1-score': 0.9400630914826499, 'support': 157}, 'micro avg': {'precision': 0.8673245614035088, 'recall': 0.9383155397390273, 'f1-score': 0.9014245014245014, 'support': 843}, 'macro avg': {'precision': 0.8888293377761768, 'recall': 0.9424620044885043, 'f1-score': 0.9141204507484169, 'support': 843}, 'weighted avg': {'precision': 0.8706402222492559, 'recall': 0.9383155397390273, 'f1-score': 0.9022291264700381, 'support': 843}}
No log	3.0	480	0.0526	0.8689	0.9276	0.8973	0.9856	{'AGE': {'precision': 0.9469026548672567, 'recall': 1.0, 'f1-score': 0.9727272727272728, 'support': 107}, 'LOC': {'precision': 0.7831325301204819, 'recall': 0.9090909090909091, 'f1-score': 0.8414239482200647, 'support': 286}, 'NAT': {'precision': 0.9096774193548387, 'recall': 0.9657534246575342, 'f1-score': 0.93687707641196, 'support': 146}, 'ORG': {'precision': 0.8943661971830986, 'recall': 0.8639455782312925, 'f1-score': 0.8788927335640138, 'support': 147}, 'PER': {'precision': 0.930379746835443, 'recall': 0.9363057324840764, 'f1-score': 0.9333333333333332, 'support': 157}, 'micro avg': {'precision': 0.8688888888888889, 'recall': 0.9276393831553974, 'f1-score': 0.8973034997131383, 'support': 843}, 'macro avg': {'precision': 0.8928917096722238, 'recall': 0.9350191288927625, 'f1-score': 0.912650872851329, 'support': 843}, 'weighted avg': {'precision': 0.872655803262326, 'recall': 0.9276393831553974, 'f1-score': 0.8982724622730086, 'support': 843}}

Framework versions

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