hw2942/bart-base-chinese-SSEC

bart-base-chinese-wallstreetcn-morning-news-market-overview-SSEC-v1

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

• Loss: 2.2056
• Accuracy: 0.6875

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	0.6914	0.5625
No log	2.0	136	0.6649	0.5938
No log	3.0	204	0.7056	0.5938
No log	4.0	272	0.6510	0.6562
No log	5.0	340	1.1325	0.6875
No log	6.0	408	1.6671	0.6875
No log	7.0	476	2.0104	0.6875
0.4905	8.0	544	1.9887	0.6875
0.4905	9.0	612	2.2172	0.6875
0.4905	10.0	680	2.2056	0.6875

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3