hw2942/chinese-roberta-wwm-ext-SSE50

chinese-roberta-wwm-ext-wallstreetcn-morning-news-market-overview-SSE50-1

This model is a fine-tuned version of hfl/chinese-roberta-wwm-ext on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.9129
• Accuracy: 0.5758

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	34	0.6851	0.4848
No log	2.0	68	0.5512	0.6364
No log	3.0	102	0.5401	0.7576
No log	4.0	136	0.6022	0.6364
No log	5.0	170	0.6753	0.6667
No log	6.0	204	1.1719	0.6061
No log	7.0	238	1.3857	0.6364
No log	8.0	272	1.7271	0.6364
No log	9.0	306	2.0849	0.5455
No log	10.0	340	1.9129	0.5758

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3