RoBERTa_Combined_Generated_v2_1500

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: 0.0555
• Precision: 0.8707
• Recall: 0.9456
• F1: 0.9066
• Accuracy: 0.9847
• Report: {'AGE': {'precision': 0.88, 'recall': 0.9565217391304348, 'f1-score': 0.9166666666666666, 'support': 46}, 'LOC': {'precision': 0.8175675675675675, 'recall': 0.9307692307692308, 'f1-score': 0.8705035971223021, 'support': 130}, 'NAT': {'precision': 0.8888888888888888, 'recall': 0.9552238805970149, 'f1-score': 0.9208633093525178, 'support': 67}, 'ORG': {'precision': 0.9038461538461539, 'recall': 0.9591836734693877, 'f1-score': 0.9306930693069307, 'support': 49}, 'PER': {'precision': 0.9473684210526315, 'recall': 0.9473684210526315, 'f1-score': 0.9473684210526315, 'support': 57}, 'micro avg': {'precision': 0.8707124010554089, 'recall': 0.9455587392550143, 'f1-score': 0.9065934065934066, 'support': 349}, 'macro avg': {'precision': 0.8875342062710484, 'recall': 0.9498133890037399, 'f1-score': 0.9172190127002098, 'support': 349}, 'weighted avg': {'precision': 0.8728017217128964, 'recall': 0.9455587392550143, 'f1-score': 0.9072605627943388, 'support': 349}}

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	150	0.0623	0.8289	0.9026	0.8642	0.9784	{'AGE': {'precision': 0.9555555555555556, 'recall': 0.9347826086956522, 'f1-score': 0.945054945054945, 'support': 46}, 'LOC': {'precision': 0.7588652482269503, 'recall': 0.823076923076923, 'f1-score': 0.7896678966789668, 'support': 130}, 'NAT': {'precision': 0.7804878048780488, 'recall': 0.9552238805970149, 'f1-score': 0.8590604026845637, 'support': 67}, 'ORG': {'precision': 0.8867924528301887, 'recall': 0.9591836734693877, 'f1-score': 0.9215686274509803, 'support': 49}, 'PER': {'precision': 0.9152542372881356, 'recall': 0.9473684210526315, 'f1-score': 0.9310344827586206, 'support': 57}, 'micro avg': {'precision': 0.8289473684210527, 'recall': 0.9025787965616046, 'f1-score': 0.8641975308641976, 'support': 349}, 'macro avg': {'precision': 0.8593910597557757, 'recall': 0.9239271013783219, 'f1-score': 0.8892772709256154, 'support': 349}, 'weighted avg': {'precision': 0.8324442477535569, 'recall': 0.9025787965616046, 'f1-score': 0.8650780208681901, 'support': 349}}
No log	2.0	300	0.0533	0.8628	0.9370	0.8984	0.9837	{'AGE': {'precision': 0.8775510204081632, 'recall': 0.9347826086956522, 'f1-score': 0.9052631578947369, 'support': 46}, 'LOC': {'precision': 0.7986577181208053, 'recall': 0.9153846153846154, 'f1-score': 0.8530465949820788, 'support': 130}, 'NAT': {'precision': 0.9014084507042254, 'recall': 0.9552238805970149, 'f1-score': 0.927536231884058, 'support': 67}, 'ORG': {'precision': 0.8867924528301887, 'recall': 0.9591836734693877, 'f1-score': 0.9215686274509803, 'support': 49}, 'PER': {'precision': 0.9473684210526315, 'recall': 0.9473684210526315, 'f1-score': 0.9473684210526315, 'support': 57}, 'micro avg': {'precision': 0.862796833773087, 'recall': 0.9369627507163324, 'f1-score': 0.8983516483516483, 'support': 349}, 'macro avg': {'precision': 0.882355612623203, 'recall': 0.9423886398398604, 'f1-score': 0.9109566066528971, 'support': 349}, 'weighted avg': {'precision': 0.8654442598290617, 'recall': 0.9369627507163324, 'f1-score': 0.8992548793471578, 'support': 349}}
No log	3.0	450	0.0555	0.8707	0.9456	0.9066	0.9847	{'AGE': {'precision': 0.88, 'recall': 0.9565217391304348, 'f1-score': 0.9166666666666666, 'support': 46}, 'LOC': {'precision': 0.8175675675675675, 'recall': 0.9307692307692308, 'f1-score': 0.8705035971223021, 'support': 130}, 'NAT': {'precision': 0.8888888888888888, 'recall': 0.9552238805970149, 'f1-score': 0.9208633093525178, 'support': 67}, 'ORG': {'precision': 0.9038461538461539, 'recall': 0.9591836734693877, 'f1-score': 0.9306930693069307, 'support': 49}, 'PER': {'precision': 0.9473684210526315, 'recall': 0.9473684210526315, 'f1-score': 0.9473684210526315, 'support': 57}, 'micro avg': {'precision': 0.8707124010554089, 'recall': 0.9455587392550143, 'f1-score': 0.9065934065934066, 'support': 349}, 'macro avg': {'precision': 0.8875342062710484, 'recall': 0.9498133890037399, 'f1-score': 0.9172190127002098, 'support': 349}, 'weighted avg': {'precision': 0.8728017217128964, 'recall': 0.9455587392550143, 'f1-score': 0.9072605627943388, 'support': 349}}

Framework versions

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