bert-base-uncased-swag

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

• Loss: 1.3863
• Accuracy: 0.2929

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: 0.0005
• train_batch_size: 16
• eval_batch_size: 16
• seed: 321
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	63	1.4088	0.2273
No log	2.0	126	1.4448	0.2323
No log	3.0	189	1.6544	0.2323
No log	4.0	252	1.8585	0.2424
No log	5.0	315	1.9976	0.2121
No log	6.0	378	1.8819	0.2071
No log	7.0	441	1.3863	0.1919
0.7104	8.0	504	1.3863	0.2929
0.7104	9.0	567	1.3863	0.1919
0.7104	10.0	630	1.3863	0.0354
0.7104	11.0	693	1.3863	0.1010
0.7104	12.0	756	1.3863	0.1364
0.7104	13.0	819	1.3863	0.0
0.7104	14.0	882	1.3863	0.1111
0.7104	15.0	945	1.3863	0.0556
1.4022	16.0	1008	1.3863	0.0253
1.4022	17.0	1071	1.3863	0.1970
1.4022	18.0	1134	1.3863	0.0
1.4022	19.0	1197	1.3863	0.0909
1.4022	20.0	1260	1.3863	0.0505

Framework versions

• Transformers 4.34.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.14.0