RoBERTa_Combined_Generated_v2_2000_Fold2

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: 0.0495
• Precision: 0.8878
• Recall: 0.9350
• F1: 0.9108
• Accuracy: 0.9859
• Report: {'AGE': {'precision': 0.9528301886792453, 'recall': 0.9901960784313726, 'f1-score': 0.9711538461538463, 'support': 102}, 'LOC': {'precision': 0.8025078369905956, 'recall': 0.927536231884058, 'f1-score': 0.8605042016806723, 'support': 276}, 'NAT': {'precision': 0.927710843373494, 'recall': 0.9447852760736196, 'f1-score': 0.9361702127659575, 'support': 163}, 'ORG': {'precision': 0.9142857142857143, 'recall': 0.8827586206896552, 'f1-score': 0.8982456140350877, 'support': 145}, 'PER': {'precision': 0.95, 'recall': 0.95, 'f1-score': 0.9500000000000001, 'support': 160}, 'micro avg': {'precision': 0.8877665544332211, 'recall': 0.9349881796690307, 'f1-score': 0.9107656879677606, 'support': 846}, 'macro avg': {'precision': 0.9094669166658098, 'recall': 0.939055241415741, 'f1-score': 0.9232147749271128, 'support': 846}, 'weighted avg': {'precision': 0.8918074920756447, 'recall': 0.9349881796690307, 'f1-score': 0.9118182159426674, 'support': 846}}

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	0.0545	0.8544	0.8948	0.8741	0.9811	{'AGE': {'precision': 0.9439252336448598, 'recall': 0.9901960784313726, 'f1-score': 0.9665071770334929, 'support': 102}, 'LOC': {'precision': 0.7580645161290323, 'recall': 0.8514492753623188, 'f1-score': 0.8020477815699659, 'support': 276}, 'NAT': {'precision': 0.8895705521472392, 'recall': 0.8895705521472392, 'f1-score': 0.8895705521472392, 'support': 163}, 'ORG': {'precision': 0.8936170212765957, 'recall': 0.8689655172413793, 'f1-score': 0.881118881118881, 'support': 145}, 'PER': {'precision': 0.9090909090909091, 'recall': 0.9375, 'f1-score': 0.923076923076923, 'support': 160}, 'micro avg': {'precision': 0.8544018058690744, 'recall': 0.8947990543735225, 'f1-score': 0.874133949191686, 'support': 846}, 'macro avg': {'precision': 0.8788536464577271, 'recall': 0.907536284636462, 'f1-score': 0.8924642629893004, 'support': 846}, 'weighted avg': {'precision': 0.8576066120839723, 'recall': 0.8947990543735225, 'f1-score': 0.8751814009754992, 'support': 846}}
No log	2.0	320	0.0587	0.8527	0.9374	0.8930	0.9832	{'AGE': {'precision': 0.9351851851851852, 'recall': 0.9901960784313726, 'f1-score': 0.961904761904762, 'support': 102}, 'LOC': {'precision': 0.7565982404692082, 'recall': 0.9347826086956522, 'f1-score': 0.8363047001620746, 'support': 276}, 'NAT': {'precision': 0.8633879781420765, 'recall': 0.9693251533742331, 'f1-score': 0.9132947976878613, 'support': 163}, 'ORG': {'precision': 0.9064748201438849, 'recall': 0.8689655172413793, 'f1-score': 0.8873239436619718, 'support': 145}, 'PER': {'precision': 0.9433962264150944, 'recall': 0.9375, 'f1-score': 0.9404388714733543, 'support': 160}, 'micro avg': {'precision': 0.8526881720430107, 'recall': 0.9373522458628841, 'f1-score': 0.893018018018018, 'support': 846}, 'macro avg': {'precision': 0.88100849007109, 'recall': 0.9401538715485274, 'f1-score': 0.9078534149780048, 'support': 846}, 'weighted avg': {'precision': 0.8597216180175263, 'recall': 0.9373522458628841, 'f1-score': 0.8947205984029104, 'support': 846}}
No log	3.0	480	0.0495	0.8878	0.9350	0.9108	0.9859	{'AGE': {'precision': 0.9528301886792453, 'recall': 0.9901960784313726, 'f1-score': 0.9711538461538463, 'support': 102}, 'LOC': {'precision': 0.8025078369905956, 'recall': 0.927536231884058, 'f1-score': 0.8605042016806723, 'support': 276}, 'NAT': {'precision': 0.927710843373494, 'recall': 0.9447852760736196, 'f1-score': 0.9361702127659575, 'support': 163}, 'ORG': {'precision': 0.9142857142857143, 'recall': 0.8827586206896552, 'f1-score': 0.8982456140350877, 'support': 145}, 'PER': {'precision': 0.95, 'recall': 0.95, 'f1-score': 0.9500000000000001, 'support': 160}, 'micro avg': {'precision': 0.8877665544332211, 'recall': 0.9349881796690307, 'f1-score': 0.9107656879677606, 'support': 846}, 'macro avg': {'precision': 0.9094669166658098, 'recall': 0.939055241415741, 'f1-score': 0.9232147749271128, 'support': 846}, 'weighted avg': {'precision': 0.8918074920756447, 'recall': 0.9349881796690307, 'f1-score': 0.9118182159426674, 'support': 846}}

Framework versions

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