bert-base-chinese-finetuned-swag-8B

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3345
• Accuracy: 0.9568

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: 3e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.091	1.0	2714	0.2826	0.9482
0.0612	2.0	5428	0.2978	0.9558
0.0171	3.0	8142	0.3345	0.9568

Framework versions

• Transformers 4.34.0
• Pytorch 1.13.1+cu116
• Datasets 2.14.5
• Tokenizers 0.14.1