gerskill-gbert-job-extended

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

• Loss: 0.0806
• Hard: {'precision': 0.7995867768595041, 'recall': 0.8524229074889867, 'f1': 0.8251599147121534, 'number': 454}
• Soft: {'precision': 0.7804878048780488, 'recall': 0.7804878048780488, 'f1': 0.7804878048780488, 'number': 82}
• Overall Precision: 0.7968
• Overall Recall: 0.8414
• Overall F1: 0.8185
• Overall Accuracy: 0.9750

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	0.1035	{'precision': 0.6715867158671587, 'recall': 0.801762114537445, 'f1': 0.7309236947791165, 'number': 454}	{'precision': 0.6105263157894737, 'recall': 0.7073170731707317, 'f1': 0.6553672316384181, 'number': 82}	0.6625	0.7873	0.7195	0.9592
No log	2.0	356	0.0762	{'precision': 0.7698744769874477, 'recall': 0.8105726872246696, 'f1': 0.7896995708154506, 'number': 454}	{'precision': 0.7532467532467533, 'recall': 0.7073170731707317, 'f1': 0.7295597484276729, 'number': 82}	0.7676	0.7948	0.7809	0.9705
0.1183	3.0	534	0.0713	{'precision': 0.7958762886597938, 'recall': 0.8502202643171806, 'f1': 0.8221512247071352, 'number': 454}	{'precision': 0.7974683544303798, 'recall': 0.7682926829268293, 'f1': 0.782608695652174, 'number': 82}	0.7961	0.8377	0.8164	0.9735
0.1183	4.0	712	0.0785	{'precision': 0.7962962962962963, 'recall': 0.8524229074889867, 'f1': 0.823404255319149, 'number': 454}	{'precision': 0.7901234567901234, 'recall': 0.7804878048780488, 'f1': 0.7852760736196319, 'number': 82}	0.7954	0.8414	0.8178	0.9739
0.1183	5.0	890	0.0806	{'precision': 0.7995867768595041, 'recall': 0.8524229074889867, 'f1': 0.8251599147121534, 'number': 454}	{'precision': 0.7804878048780488, 'recall': 0.7804878048780488, 'f1': 0.7804878048780488, 'number': 82}	0.7968	0.8414	0.8185	0.9750

Framework versions

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