vdsouza1
/

bert-finetuned-ner

Token Classification

generated_from_keras_callback

Inference Endpoints

Model card Files Files and versions Community

vdsouza1 commited on Apr 15, 2022

Commit

d081130

•

1 Parent(s): 3dea930

End of training

Files changed (2) hide show

README.md +5 -3
tf_model.h5 +1 -1

README.md CHANGED Viewed

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.1293
-- Validation Loss: 0.0559
-- Epoch: 0
 ## Model description
@@ -43,6 +43,8 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
 | 0.1293     | 0.0559          | 0     |
 ### Framework versions

 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Train Loss: 0.0253
+- Validation Loss: 0.0587
+- Epoch: 2
 ## Model description
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
 | 0.1293     | 0.0559          | 0     |
+| 0.0407     | 0.0552          | 1     |
+| 0.0253     | 0.0587          | 2     |
 ### Framework versions

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd88bfe75ece2ab5aa625dca3e5cb5e98d08f3769c277a5fb80c6f21e1d3a909
 size 435861524

 version https://git-lfs.github.com/spec/v1
+oid sha256:c5f7d95873606a43d0416a3c7aa093ab9a3fa030f0ccce79e13954d69da8749e
 size 435861524