mdeniz1
/

bert-finetuned-absa-turkish

Token Classification

generated_from_keras_callback

Model card Files Files and versions

mdeniz1 commited on Jan 9, 2024

Commit

52c0b91

·

1 Parent(s): 439ffe4

Training in progress epoch 2

Files changed (2) hide show

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

README.md CHANGED Viewed

@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [dbmdz/bert-base-turkish-uncased](https://huggingface.co/dbmdz/bert-base-turkish-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 3.1436
-- Validation Loss: 1.9775
-- Epoch: 0
 ## Model description
@@ -44,6 +44,8 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
 | 3.1436     | 1.9775          | 0     |
 ### Framework versions

 This model is a fine-tuned version of [dbmdz/bert-base-turkish-uncased](https://huggingface.co/dbmdz/bert-base-turkish-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Train Loss: 2.1606
+- Validation Loss: 1.9498
+- Epoch: 2
 ## Model description
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
 | 3.1436     | 1.9775          | 0     |
+| 2.2359     | 1.9539          | 1     |
+| 2.1606     | 1.9498          | 2     |
 ### Framework versions

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb115e40df51346d0bdb451e97dfe50e4aa4ae12f101b9dddfc78defc1e82e2d
 size 445523416

 version https://git-lfs.github.com/spec/v1
+oid sha256:23b6ca29db726ea07cb901a6d4e6de73abd9ff8c77b111263f4a3975d537fef2
 size 445523416