RoBERTa_Combined_Generated_v2_2000_Fold1

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: 0.0542
• Precision: 0.8803
• Recall: 0.9358
• F1: 0.9072
• Accuracy: 0.9861
• Report: {'AGE': {'precision': 0.9491525423728814, 'recall': 0.9911504424778761, 'f1-score': 0.9696969696969698, 'support': 113}, 'LOC': {'precision': 0.775, 'recall': 0.915129151291513, 'f1-score': 0.8392554991539763, 'support': 271}, 'NAT': {'precision': 0.9176470588235294, 'recall': 0.9512195121951219, 'f1-score': 0.9341317365269461, 'support': 164}, 'ORG': {'precision': 0.9230769230769231, 'recall': 0.9230769230769231, 'f1-score': 0.9230769230769231, 'support': 130}, 'PER': {'precision': 0.967948717948718, 'recall': 0.9263803680981595, 'f1-score': 0.9467084639498432, 'support': 163}, 'micro avg': {'precision': 0.8803131991051454, 'recall': 0.9357907253269917, 'f1-score': 0.9072046109510086, 'support': 841}, 'macro avg': {'precision': 0.9065650484444104, 'recall': 0.9413912794279188, 'f1-score': 0.9225739184809317, 'support': 841}, 'weighted avg': {'precision': 0.8865029678487937, 'recall': 0.9357907253269917, 'f1-score': 0.9090666852089522, 'support': 841}}

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	0.0557	0.8449	0.9132	0.8777	0.9828	{'AGE': {'precision': 0.9411764705882353, 'recall': 0.9911504424778761, 'f1-score': 0.9655172413793104, 'support': 113}, 'LOC': {'precision': 0.7467948717948718, 'recall': 0.8597785977859779, 'f1-score': 0.7993138936535162, 'support': 271}, 'NAT': {'precision': 0.8603351955307262, 'recall': 0.9390243902439024, 'f1-score': 0.8979591836734694, 'support': 164}, 'ORG': {'precision': 0.8613138686131386, 'recall': 0.9076923076923077, 'f1-score': 0.8838951310861423, 'support': 130}, 'PER': {'precision': 0.9320987654320988, 'recall': 0.9263803680981595, 'f1-score': 0.9292307692307692, 'support': 163}, 'micro avg': {'precision': 0.8448844884488449, 'recall': 0.9131985731272295, 'f1-score': 0.8777142857142858, 'support': 841}, 'macro avg': {'precision': 0.8683438343918141, 'recall': 0.9248052212596447, 'f1-score': 0.8951832438046414, 'support': 841}, 'weighted avg': {'precision': 0.8486708979608324, 'recall': 0.9131985731272295, 'f1-score': 0.8791365065448608, 'support': 841}}
No log	2.0	320	0.0581	0.8686	0.9429	0.9042	0.9847	{'AGE': {'precision': 0.9411764705882353, 'recall': 0.9911504424778761, 'f1-score': 0.9655172413793104, 'support': 113}, 'LOC': {'precision': 0.7832817337461301, 'recall': 0.933579335793358, 'f1-score': 0.8518518518518519, 'support': 271}, 'NAT': {'precision': 0.8516483516483516, 'recall': 0.9451219512195121, 'f1-score': 0.8959537572254336, 'support': 164}, 'ORG': {'precision': 0.9166666666666666, 'recall': 0.9307692307692308, 'f1-score': 0.9236641221374045, 'support': 130}, 'PER': {'precision': 0.9681528662420382, 'recall': 0.9325153374233128, 'f1-score': 0.9500000000000001, 'support': 163}, 'micro avg': {'precision': 0.8685651697699891, 'recall': 0.9429250891795482, 'f1-score': 0.9042189281641961, 'support': 841}, 'macro avg': {'precision': 0.8921852177782844, 'recall': 0.9466272595366579, 'f1-score': 0.9173973945188001, 'support': 841}, 'weighted avg': {'precision': 0.8742784834198815, 'recall': 0.9429250891795482, 'f1-score': 0.9058478622955382, 'support': 841}}
No log	3.0	480	0.0542	0.8803	0.9358	0.9072	0.9861	{'AGE': {'precision': 0.9491525423728814, 'recall': 0.9911504424778761, 'f1-score': 0.9696969696969698, 'support': 113}, 'LOC': {'precision': 0.775, 'recall': 0.915129151291513, 'f1-score': 0.8392554991539763, 'support': 271}, 'NAT': {'precision': 0.9176470588235294, 'recall': 0.9512195121951219, 'f1-score': 0.9341317365269461, 'support': 164}, 'ORG': {'precision': 0.9230769230769231, 'recall': 0.9230769230769231, 'f1-score': 0.9230769230769231, 'support': 130}, 'PER': {'precision': 0.967948717948718, 'recall': 0.9263803680981595, 'f1-score': 0.9467084639498432, 'support': 163}, 'micro avg': {'precision': 0.8803131991051454, 'recall': 0.9357907253269917, 'f1-score': 0.9072046109510086, 'support': 841}, 'macro avg': {'precision': 0.9065650484444104, 'recall': 0.9413912794279188, 'f1-score': 0.9225739184809317, 'support': 841}, 'weighted avg': {'precision': 0.8865029678487937, 'recall': 0.9357907253269917, 'f1-score': 0.9090666852089522, 'support': 841}}

Framework versions

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