RoBERTa_Combined_Generated_v2_2000

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: 0.0544
• Precision: 0.8678
• Recall: 0.9397
• F1: 0.9024
• Accuracy: 0.9831
• Report: {'AGE': {'precision': 0.9873417721518988, 'recall': 1.0, 'f1-score': 0.9936305732484078, 'support': 78}, 'LOC': {'precision': 0.7476190476190476, 'recall': 0.9289940828402367, 'f1-score': 0.8284960422163588, 'support': 169}, 'NAT': {'precision': 0.9148936170212766, 'recall': 0.945054945054945, 'f1-score': 0.9297297297297297, 'support': 91}, 'ORG': {'precision': 0.9032258064516129, 'recall': 0.9130434782608695, 'f1-score': 0.9081081081081082, 'support': 92}, 'PER': {'precision': 0.9494949494949495, 'recall': 0.9306930693069307, 'f1-score': 0.9400000000000001, 'support': 101}, 'micro avg': {'precision': 0.8678260869565217, 'recall': 0.9397363465160076, 'f1-score': 0.9023508137432188, 'support': 531}, 'macro avg': {'precision': 0.900515038547757, 'recall': 0.9435571150925964, 'f1-score': 0.9199928906605208, 'support': 531}, 'weighted avg': {'precision': 0.8768575527626019, 'recall': 0.9397363465160076, 'f1-score': 0.9051042696785155, 'support': 531}}

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	200	0.0914	0.8177	0.9209	0.8663	0.9761	{'AGE': {'precision': 0.975, 'recall': 1.0, 'f1-score': 0.9873417721518987, 'support': 78}, 'LOC': {'precision': 0.6784140969162996, 'recall': 0.9112426035502958, 'f1-score': 0.7777777777777777, 'support': 169}, 'NAT': {'precision': 0.8854166666666666, 'recall': 0.9340659340659341, 'f1-score': 0.909090909090909, 'support': 91}, 'ORG': {'precision': 0.8404255319148937, 'recall': 0.8586956521739131, 'f1-score': 0.849462365591398, 'support': 92}, 'PER': {'precision': 0.9207920792079208, 'recall': 0.9207920792079208, 'f1-score': 0.9207920792079208, 'support': 101}, 'micro avg': {'precision': 0.8177257525083612, 'recall': 0.9209039548022598, 'f1-score': 0.866253321523472, 'support': 531}, 'macro avg': {'precision': 0.8600096749411561, 'recall': 0.9249592537996127, 'f1-score': 0.8888929807639808, 'support': 531}, 'weighted avg': {'precision': 0.8316272090050688, 'recall': 0.9209039548022598, 'f1-score': 0.8706872185197247, 'support': 531}}
No log	2.0	400	0.0520	0.8596	0.9228	0.8901	0.9825	{'AGE': {'precision': 0.9512195121951219, 'recall': 1.0, 'f1-score': 0.975, 'support': 78}, 'LOC': {'precision': 0.7317073170731707, 'recall': 0.8875739644970414, 'f1-score': 0.8021390374331551, 'support': 169}, 'NAT': {'precision': 0.8865979381443299, 'recall': 0.945054945054945, 'f1-score': 0.9148936170212766, 'support': 91}, 'ORG': {'precision': 0.9425287356321839, 'recall': 0.8913043478260869, 'f1-score': 0.9162011173184358, 'support': 92}, 'PER': {'precision': 0.9494949494949495, 'recall': 0.9306930693069307, 'f1-score': 0.9400000000000001, 'support': 101}, 'micro avg': {'precision': 0.8596491228070176, 'recall': 0.9227871939736346, 'f1-score': 0.8900999091734787, 'support': 531}, 'macro avg': {'precision': 0.8923096905079513, 'recall': 0.9309252653370008, 'f1-score': 0.9096467543545735, 'support': 531}, 'weighted avg': {'precision': 0.868447654397119, 'recall': 0.9227871939736346, 'f1-score': 0.8928386426900856, 'support': 531}}
0.0789	3.0	600	0.0544	0.8678	0.9397	0.9024	0.9831	{'AGE': {'precision': 0.9873417721518988, 'recall': 1.0, 'f1-score': 0.9936305732484078, 'support': 78}, 'LOC': {'precision': 0.7476190476190476, 'recall': 0.9289940828402367, 'f1-score': 0.8284960422163588, 'support': 169}, 'NAT': {'precision': 0.9148936170212766, 'recall': 0.945054945054945, 'f1-score': 0.9297297297297297, 'support': 91}, 'ORG': {'precision': 0.9032258064516129, 'recall': 0.9130434782608695, 'f1-score': 0.9081081081081082, 'support': 92}, 'PER': {'precision': 0.9494949494949495, 'recall': 0.9306930693069307, 'f1-score': 0.9400000000000001, 'support': 101}, 'micro avg': {'precision': 0.8678260869565217, 'recall': 0.9397363465160076, 'f1-score': 0.9023508137432188, 'support': 531}, 'macro avg': {'precision': 0.900515038547757, 'recall': 0.9435571150925964, 'f1-score': 0.9199928906605208, 'support': 531}, 'weighted avg': {'precision': 0.8768575527626019, 'recall': 0.9397363465160076, 'f1-score': 0.9051042696785155, 'support': 531}}

Framework versions

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