gerskill-gbert-job

This model is a fine-tuned version of dathi103/gbert-job on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1135
• Hard: {'precision': 0.7519685039370079, 'recall': 0.8377192982456141, 'f1': 0.7925311203319502, 'number': 456}
• Soft: {'precision': 0.6739130434782609, 'recall': 0.7560975609756098, 'f1': 0.7126436781609194, 'number': 82}
• Overall Precision: 0.74
• Overall Recall: 0.8253
• Overall F1: 0.7803
• Overall Accuracy: 0.9647

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Hard	Soft	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
No log	1.0	178	0.1201	{'precision': 0.6016949152542372, 'recall': 0.7785087719298246, 'f1': 0.678776290630975, 'number': 456}	{'precision': 0.5894736842105263, 'recall': 0.6829268292682927, 'f1': 0.632768361581921, 'number': 82}	0.6	0.7639	0.6721	0.9508
No log	2.0	356	0.1010	{'precision': 0.6853281853281853, 'recall': 0.7785087719298246, 'f1': 0.728952772073922, 'number': 456}	{'precision': 0.632183908045977, 'recall': 0.6707317073170732, 'f1': 0.6508875739644969, 'number': 82}	0.6777	0.7621	0.7174	0.9603
0.1417	3.0	534	0.1026	{'precision': 0.7030075187969925, 'recall': 0.8201754385964912, 'f1': 0.757085020242915, 'number': 456}	{'precision': 0.65625, 'recall': 0.7682926829268293, 'f1': 0.7078651685393258, 'number': 82}	0.6959	0.8123	0.7496	0.9598
0.1417	4.0	712	0.1122	{'precision': 0.7311411992263056, 'recall': 0.8289473684210527, 'f1': 0.776978417266187, 'number': 456}	{'precision': 0.6464646464646465, 'recall': 0.7804878048780488, 'f1': 0.7071823204419891, 'number': 82}	0.7175	0.8216	0.7660	0.9616
0.1417	5.0	890	0.1135	{'precision': 0.7519685039370079, 'recall': 0.8377192982456141, 'f1': 0.7925311203319502, 'number': 456}	{'precision': 0.6739130434782609, 'recall': 0.7560975609756098, 'f1': 0.7126436781609194, 'number': 82}	0.74	0.8253	0.7803	0.9647

Framework versions

• Transformers 4.38.1
• Pytorch 2.1.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2