BeardedJohn
/

bert-ner-wikiann

Token Classification

generated_from_keras_callback

Model card Files Files and versions

BeardedJohn commited on Feb 6, 2023

Commit

449fd59

·

1 Parent(s): bdf33ae

Upload TFBertForTokenClassification

Files changed (2) hide show

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

README.md CHANGED Viewed

@@ -14,8 +14,8 @@ probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [BeardedJohn/bert-finetuned-ner-ubb-conll-endava-only-misc-v2](https://huggingface.co/BeardedJohn/bert-finetuned-ner-ubb-conll-endava-only-misc-v2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.2614
-- Validation Loss: 0.4496
 - Epoch: 2
 ## Model description
@@ -42,9 +42,9 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.6485     | 0.4999          | 0     |
-| 0.3731     | 0.4518          | 1     |
-| 0.2614     | 0.4496          | 2     |
 ### Framework versions

 This model is a fine-tuned version of [BeardedJohn/bert-finetuned-ner-ubb-conll-endava-only-misc-v2](https://huggingface.co/BeardedJohn/bert-finetuned-ner-ubb-conll-endava-only-misc-v2) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Train Loss: 0.1926
+- Validation Loss: 0.3131
 - Epoch: 2
 ## Model description
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
+| 0.3988     | 0.3206          | 0     |
+| 0.2620     | 0.2997          | 1     |
+| 0.1926     | 0.3131          | 2     |
 ### Framework versions

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aba34689892d3b41246df9bb0cf51a4dbf07b58c56480abf532214ac1205d72
 size 431179820

 version https://git-lfs.github.com/spec/v1
+oid sha256:ed58e29b73d7e70c3fd15b22d5f7e4d88086bd716f15ba0a61a824402785511e
 size 431179820