cgt
/

Roberta-wwm-ext-large-qa

Question Answering Transformers PyTorch

bert generated_from_trainer Inference Endpoints

Model card Files Files and versions Community

cgt commited on Nov 1, 2022

Commit

b3f991e

•

1 Parent(s): 5b3c1f0

update model card README.md

Files changed (1) hide show

README.md +3 -5

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [hfl/chinese-roberta-wwm-ext-large](https://huggingface.co/hfl/chinese-roberta-wwm-ext-large) on the cmrc2018 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2259
 ## Model description
@@ -41,15 +41,13 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.3521        | 1.0   | 1200 | 1.1223          |
-| 1.0266        | 2.0   | 2400 | 1.1404          |
-| 0.8443        | 3.0   | 3600 | 1.2259          |
 ### Framework versions

 This model is a fine-tuned version of [hfl/chinese-roberta-wwm-ext-large](https://huggingface.co/hfl/chinese-roberta-wwm-ext-large) on the cmrc2018 dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.1416
 ## Model description
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 1
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 1.3584        | 1.0   | 1200 | 1.1416          |
 ### Framework versions