hw2942/chinese-bigbird-SSE50

chinese-bigbird-wwm-base-4096-wallstreetcn-morning-news-market-overview-SSE50-v9

This model is a fine-tuned version of Lowin/chinese-bigbird-wwm-base-4096 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.4472
• Accuracy: 0.7879

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	68	1.0269	0.8485
No log	2.0	136	1.3666	0.8182
No log	3.0	204	1.0301	0.8485
No log	4.0	272	1.1611	0.8485
No log	5.0	340	1.0784	0.8182
No log	6.0	408	1.3625	0.7879
No log	7.0	476	1.3928	0.7879
0.029	8.0	544	1.4454	0.7879
0.029	9.0	612	1.4441	0.7879
0.029	10.0	680	1.4472	0.7879

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.0