Downloads · 30 days
5
1% of all-time downloads
hw2942/Erlangshen-Longformer-110M-finetuning-wallstreetcn-morning-news-market-overview-open-000001SH-v1
Erlangshen-Longformer-110M-finetuning-wallstreetcn-morning-news-market-overview-open-000001SH-v1 is a text classification model from hw2942. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
5
1% of all-time downloads
All-time downloads
459
Public
Repo size
5.2 GB
Likes
0
Public
Click a slice to open those files.
.bin477 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of IDEA-CCNL/Erlangshen-Longformer-110M on the dataset of Wallstreetcn Morning News Market Overview with overnight index (000001.SH) movement labels. It achieves the following results on the best evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 38 | 0.6779 | 0.5862 |
| No log | 2.0 | 76 | 0.6771 | 0.5862 |
| No log | 3.0 | 114 | 0.6752 | 0.5862 |
| No log | 4.0 | 152 | 0.7186 | 0.6552 |
| No log | 5.0 | 190 | 0.7296 | 0.5862 |
| No log | 6.0 | 228 | 0.7948 | 0.5862 |
| No log | 7.0 | 266 | 0.9698 | 0.6207 |
| No log | 8.0 | 304 | 1.0275 | 0.5862 |
| No log | 9.0 | 342 | 1.0434 | 0.6207 |
| No log | 10.0 | 380 | 1.0603 | 0.5862 |