aalogan
/

bert-ner-nsm2

Token Classification

generated_from_keras_callback

Inference Endpoints

Model card Files Files and versions Community

aalogan commited on Jul 21, 2022

Commit

e0bedf7

•

1 Parent(s): 30bb8e5

Training in progress epoch 3

Files changed (2) hide show

README.md +6 -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-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.4885
-- Validation Loss: 0.2361
-- Epoch: 0
 ## Model description
@@ -43,6 +43,9 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
 | 0.4885     | 0.2361          | 0     |
 ### Framework versions

 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Train Loss: 0.0649
+- Validation Loss: 0.1762
+- Epoch: 3
 ## Model description
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
 | 0.4885     | 0.2361          | 0     |
+| 0.1547     | 0.1920          | 1     |
+| 0.0966     | 0.1648          | 2     |
+| 0.0649     | 0.1762          | 3     |
 ### Framework versions

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a535a4a302e81677c93201930f2f6b8ec20b97751c950f70b72f7a4fc80e5c4e
 size 431204428

 version https://git-lfs.github.com/spec/v1
+oid sha256:bd39ba19123146b373755e65a8f2461f43822cd26c7e6c5ab0536714af21a983
 size 431204428