jb_sytem_bin_judge_base_qa

This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5387
• Accuracy: 0.8955
• Recall: 0.8948
• Precision: 0.8563
• F1: 0.8751

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: 6
• eval_batch_size: 6
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Recall	Precision	F1
0.3421	1.0	1708	0.4182	0.8920	0.8991	0.8465	0.8720
0.1548	2.0	3416	0.5443	0.8797	0.9099	0.8170	0.8609
0.2665	3.0	5124	0.4797	0.8982	0.8412	0.9032	0.8711
0.2009	4.0	6832	0.4726	0.8973	0.8884	0.8643	0.8762
0.0602	5.0	8540	0.5387	0.8955	0.8948	0.8563	0.8751

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2