RoBERTa_Combined_Generated_v2_1000

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: 0.0510
• Precision: 0.8644
• Recall: 0.9375
• F1: 0.8995
• Accuracy: 0.9844
• Report: {'AGE': {'precision': 0.9722222222222222, 'recall': 1.0, 'f1-score': 0.9859154929577464, 'support': 35}, 'LOC': {'precision': 0.7741935483870968, 'recall': 0.9411764705882353, 'f1-score': 0.8495575221238938, 'support': 102}, 'NAT': {'precision': 0.9622641509433962, 'recall': 0.9622641509433962, 'f1-score': 0.9622641509433962, 'support': 53}, 'ORG': {'precision': 0.8421052631578947, 'recall': 0.8421052631578947, 'f1-score': 0.8421052631578947, 'support': 38}, 'PER': {'precision': 0.9318181818181818, 'recall': 0.9318181818181818, 'f1-score': 0.9318181818181818, 'support': 44}, 'micro avg': {'precision': 0.864406779661017, 'recall': 0.9375, 'f1-score': 0.8994708994708995, 'support': 272}, 'macro avg': {'precision': 0.8965206733057582, 'recall': 0.9354728133015415, 'f1-score': 0.9143321222002226, 'support': 272}, 'weighted avg': {'precision': 0.8713070577693443, 'recall': 0.9375, 'f1-score': 0.9013305496696996, 'support': 272}}

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	100	0.0653	0.8305	0.9007	0.8642	0.9804	{'AGE': {'precision': 0.9722222222222222, 'recall': 1.0, 'f1-score': 0.9859154929577464, 'support': 35}, 'LOC': {'precision': 0.7747747747747747, 'recall': 0.8431372549019608, 'f1-score': 0.8075117370892019, 'support': 102}, 'NAT': {'precision': 0.85, 'recall': 0.9622641509433962, 'f1-score': 0.9026548672566371, 'support': 53}, 'ORG': {'precision': 0.775, 'recall': 0.8157894736842105, 'f1-score': 0.7948717948717949, 'support': 38}, 'PER': {'precision': 0.875, 'recall': 0.9545454545454546, 'f1-score': 0.9130434782608695, 'support': 44}, 'micro avg': {'precision': 0.8305084745762712, 'recall': 0.9007352941176471, 'f1-score': 0.8641975308641974, 'support': 272}, 'macro avg': {'precision': 0.8493993993993992, 'recall': 0.9151472668150046, 'f1-score': 0.8807994740872498, 'support': 272}, 'weighted avg': {'precision': 0.8310838411941353, 'recall': 0.9007352941176471, 'f1-score': 0.8643124582714262, 'support': 272}}
No log	2.0	200	0.0516	0.8462	0.9301	0.8862	0.9825	{'AGE': {'precision': 0.9722222222222222, 'recall': 1.0, 'f1-score': 0.9859154929577464, 'support': 35}, 'LOC': {'precision': 0.7619047619047619, 'recall': 0.9411764705882353, 'f1-score': 0.8421052631578947, 'support': 102}, 'NAT': {'precision': 0.9259259259259259, 'recall': 0.9433962264150944, 'f1-score': 0.9345794392523364, 'support': 53}, 'ORG': {'precision': 0.8157894736842105, 'recall': 0.8157894736842105, 'f1-score': 0.8157894736842104, 'support': 38}, 'PER': {'precision': 0.9111111111111111, 'recall': 0.9318181818181818, 'f1-score': 0.9213483146067416, 'support': 44}, 'micro avg': {'precision': 0.8461538461538461, 'recall': 0.9301470588235294, 'f1-score': 0.8861646234676006, 'support': 272}, 'macro avg': {'precision': 0.8773906989696464, 'recall': 0.9264360705011445, 'f1-score': 0.899947596731786, 'support': 272}, 'weighted avg': {'precision': 0.8525920090258327, 'recall': 0.9301470588235294, 'f1-score': 0.8877713794805031, 'support': 272}}
No log	3.0	300	0.0510	0.8644	0.9375	0.8995	0.9844	{'AGE': {'precision': 0.9722222222222222, 'recall': 1.0, 'f1-score': 0.9859154929577464, 'support': 35}, 'LOC': {'precision': 0.7741935483870968, 'recall': 0.9411764705882353, 'f1-score': 0.8495575221238938, 'support': 102}, 'NAT': {'precision': 0.9622641509433962, 'recall': 0.9622641509433962, 'f1-score': 0.9622641509433962, 'support': 53}, 'ORG': {'precision': 0.8421052631578947, 'recall': 0.8421052631578947, 'f1-score': 0.8421052631578947, 'support': 38}, 'PER': {'precision': 0.9318181818181818, 'recall': 0.9318181818181818, 'f1-score': 0.9318181818181818, 'support': 44}, 'micro avg': {'precision': 0.864406779661017, 'recall': 0.9375, 'f1-score': 0.8994708994708995, 'support': 272}, 'macro avg': {'precision': 0.8965206733057582, 'recall': 0.9354728133015415, 'f1-score': 0.9143321222002226, 'support': 272}, 'weighted avg': {'precision': 0.8713070577693443, 'recall': 0.9375, 'f1-score': 0.9013305496696996, 'support': 272}}

Framework versions

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