Training in progress epoch 4

README.md

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0728
-- Validation Loss: 0.2701
-- Epoch: 3
+- Train Loss: 0.0543
+- Validation Loss: 0.2919
+- Epoch: 4
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 0.1523     | 0.2540          | 1     |
 | 0.1035     | 0.2643          | 2     |
 | 0.0728     | 0.2701          | 3     |
+| 0.0543     | 0.2919          | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d542907db2f9d9961f1d5f47a0de56bf6cb5c35c627cd30fb12679db26ece92
+oid sha256:696420ae2b966586cfa0492c37350e38f3b22f8c4bc1add2bbca64981a102ed5
 size 437766324