Training in progress epoch 5

README.md

@@ -14,10 +14,10 @@ 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: 0.3711
-- Validation Loss: 0.4883
-- Train Accuracy: 0.6923
-- Epoch: 3
+- Train Loss: 0.2492
+- Validation Loss: 0.6244
+- Train Accuracy: 0.6410
+- Epoch: 5
 
 ## Model description
 
@@ -47,6 +47,8 @@ The following hyperparameters were used during training:
 | 0.6048     | 0.6772          | 0.5897         | 1     |
 | 0.4599     | 0.4915          | 0.7692         | 2     |
 | 0.3711     | 0.4883          | 0.6923         | 3     |
+| 0.3174     | 0.5588          | 0.7436         | 4     |
+| 0.2492     | 0.6244          | 0.6410         | 5     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd472fb1fff4a891567231afd6d9ace3c64cc031a6661b8f582f2bfa17ec39d5
+oid sha256:6e8707fcbb75967f3e8fe37da92db816a9100ae3f28302b32aaaad1728bedcb5
 size 267955144