Training in progress epoch 3

README.md

@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [dbmdz/bert-base-turkish-cased](https://huggingface.co/dbmdz/bert-base-turkish-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.5476
-- Validation Loss: 0.4605
-- Train F1: 0.7273
-- Epoch: 0
+- Train Loss: 0.0187
+- Validation Loss: 0.4749
+- Train F1: 0.8352
+- Epoch: 3
 
 ## Model description
 
@@ -45,6 +45,9 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Train F1 | Epoch |
 |:----------:|:---------------:|:--------:|:-----:|
 | 0.5476     | 0.4605          | 0.7273   | 0     |
+| 0.1931     | 0.3489          | 0.8370   | 1     |
+| 0.0493     | 0.4687          | 0.8287   | 2     |
+| 0.0187     | 0.4749          | 0.8352   | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1716295921.tm211pc.548661.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:283bfa464cf46eca1a6aee0e5e30f0ab284e2795b4b105126f1f4d45abb3d2f6
-size 3665801
+oid sha256:d0c8e9495beefbf4b8a8403ff9be86a5b261f8f7edcd61592501d51429f7af72
+size 3666434

logs/validation/events.out.tfevents.1716295996.tm211pc.548661.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:022b216fef63b12b9c1a868c5b2d3ec8b29ef389f6fd5ba13d00000653a2a000
-size 232
+oid sha256:e2c46cadb2a6b74843836d6de9c3a7f38f21d0f08dce15d8798e91af47b961a8
+size 700

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97dc9da9a9ef0178399f3a9f55d8e07b9d9486788ab2512f1205397c89cf1c62
+oid sha256:cf6218934f5b2d2d46e1a5c09eb8d8695440f3019a8e186f1f1cc1eb2bdd8406
 size 442763544