Training in progress epoch 0

README.md

@@ -14,11 +14,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.2527
-- Train Accuracy: 0.9084
-- Validation Loss: 0.3977
-- Validation Accuracy: 0.8491
-- Epoch: 2
+- Train Loss: 0.4349
+- Train Accuracy: 0.8150
+- Validation Loss: 0.3635
+- Validation Accuracy: 0.8635
+- Epoch: 0
 
 ## Model description
 
@@ -44,9 +44,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| 0.4381     | 0.8144         | 0.3739          | 0.8465              | 0     |
-| 0.3230     | 0.8734         | 0.3783          | 0.8478              | 1     |
-| 0.2527     | 0.9084         | 0.3977          | 0.8491              | 2     |
+| 0.4349     | 0.8150         | 0.3635          | 0.8635              | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e1ae835510cd12743c90cc6023bf657d88d4f244b43a88afe2ce1c2c3ebb0ca
+oid sha256:6ae5a0a0fc2a4ea728e8b587a5729669070b28ca3b2a68542ce1c5607a4c370e
 size 267951896