Training in progress epoch 3

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: 0.6943
-- Validation Loss: 0.6928
-- Train Accuracy: 0.5128
-- Epoch: 0
+- Train Loss: 0.2213
+- Validation Loss: 0.2287
+- Train Accuracy: 0.9231
+- Epoch: 3
 
 ## Model description
 
@@ -44,6 +44,9 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
 | 0.6943     | 0.6928          | 0.5128         | 0     |
+| 0.6642     | 0.5426          | 0.8718         | 1     |
+| 0.4149     | 0.2977          | 0.9231         | 2     |
+| 0.2213     | 0.2287          | 0.9231         | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c8c96b5fff05c8ae3e9befd101715da4403ac0db05f09913f92b28b57485e22
+oid sha256:087e2861694c24d361724a84adddc294e1644e44fedc9cd296f167a84fee58bf
 size 267951808