TextAttack Model CardThis
bert-base-uncased
model was fine-tuned for sequence classification using TextAttack
and the ag_news dataset loaded using the
nlp
library. The model was fine-tuned
for 5 epochs with a batch size of 16, a learning
rate of 3e-05, and a maximum sequence length of 128.
Since this was a classification task, the model was trained with a cross-entropy loss function.
The best score the model achieved on this task was 0.9514473684210526, as measured by the
eval set accuracy, found after 3 epochs.
Runs of textattack bert-base-uncased-ag-news on huggingface.co
2.1K
Total runs
44
24-hour runs
81
3-day runs
158
7-day runs
-37
30-day runs
More Information About bert-base-uncased-ag-news huggingface.co Model
bert-base-uncased-ag-news huggingface.co
bert-base-uncased-ag-news huggingface.co is an AI model on huggingface.co that provides bert-base-uncased-ag-news's model effect (), which can be used instantly with this textattack bert-base-uncased-ag-news model. huggingface.co supports a free trial of the bert-base-uncased-ag-news model, and also provides paid use of the bert-base-uncased-ag-news. Support call bert-base-uncased-ag-news model through api, including Node.js, Python, http.
bert-base-uncased-ag-news huggingface.co is an online trial and call api platform, which integrates bert-base-uncased-ag-news's modeling effects, including api services, and provides a free online trial of bert-base-uncased-ag-news, you can try bert-base-uncased-ag-news online for free by clicking the link below.
textattack bert-base-uncased-ag-news online free url in huggingface.co:
bert-base-uncased-ag-news is an open source model from GitHub that offers a free installation service, and any user can find bert-base-uncased-ag-news on GitHub to install. At the same time, huggingface.co provides the effect of bert-base-uncased-ag-news install, users can directly use bert-base-uncased-ag-news installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
bert-base-uncased-ag-news install url in huggingface.co: