bert-base-uncased-IBM-argQ-30k-finetuned-sufficiency-dagstuhl

This model is a fine-tuned version of jakub014/bert-base-uncased-IBM-argQ-30k on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5933
• Accuracy: 0.6984

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: 16
• eval_batch_size: 16
• 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	Accuracy
No log	1.0	16	0.5933	0.6984
No log	2.0	32	0.6388	0.6190
No log	3.0	48	0.7638	0.6349
No log	4.0	64	0.8638	0.6190
No log	5.0	80	0.9086	0.6349

Framework versions

• Transformers 4.27.3
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2