Upload TFBertForSequenceClassification

README.md

@@ -15,10 +15,10 @@ 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: 0.1051
-- Validation Loss: 0.6202
-- Train F1: 0.8331
-- Epoch: 4
+- Train Loss: 0.0665
+- Validation Loss: 0.5903
+- Train F1: 0.8329
+- Epoch: 5
 
 ## Model description
 
@@ -44,11 +44,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train F1 | Epoch |
 |:----------:|:---------------:|:--------:|:-----:|
-| 0.6587     | 0.5462          | 0.8149   | 0     |
-| 0.3940     | 0.4770          | 0.8334   | 1     |
-| 0.2685     | 0.5156          | 0.8399   | 2     |
-| 0.1741     | 0.5909          | 0.8276   | 3     |
-| 0.1051     | 0.6202          | 0.8331   | 4     |
+| 0.6321     | 0.4654          | 0.8258   | 0     |
+| 0.4053     | 0.4943          | 0.8241   | 1     |
+| 0.2884     | 0.4143          | 0.8596   | 2     |
+| 0.1851     | 0.4852          | 0.8469   | 3     |
+| 0.1185     | 0.5479          | 0.8424   | 4     |
+| 0.0665     | 0.5903          | 0.8329   | 5     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:037e5df21459d876f28e0cb510f8ca384b95e38cdcace9711549d22de278ff5c
+oid sha256:26f62d62222ec0a63542ae151f6892ca6b67b010ccbcc63fda9ff5a3d8ab5b43
 size 438226204