Training in progress epoch 20

README.md

@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.4423
-- Validation Loss: 0.8468
-- Train Accuracy: 0.9067
-- Epoch: 9
+- Train Loss: 0.0761
+- Validation Loss: 0.4911
+- Train Accuracy: 0.8833
+- Epoch: 20
 
 ## Model description
 
@@ -54,6 +54,17 @@ The following hyperparameters were used during training:
 | 0.8233     | 1.1592          | 0.8867         | 7     |
 | 0.6009     | 0.9746          | 0.9033         | 8     |
 | 0.4423     | 0.8468          | 0.9067         | 9     |
+| 0.3338     | 0.7524          | 0.8967         | 10    |
+| 0.2628     | 0.6865          | 0.8967         | 11    |
+| 0.2142     | 0.6403          | 0.8933         | 12    |
+| 0.1774     | 0.6060          | 0.8933         | 13    |
+| 0.1522     | 0.5770          | 0.89           | 14    |
+| 0.1316     | 0.5526          | 0.89           | 15    |
+| 0.1163     | 0.5336          | 0.8867         | 16    |
+| 0.1027     | 0.5190          | 0.89           | 17    |
+| 0.0923     | 0.5043          | 0.8933         | 18    |
+| 0.0851     | 0.4970          | 0.8867         | 19    |
+| 0.0761     | 0.4911          | 0.8833         | 20    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93d7f71240f4c9626e9eec9cc86ccf88469dc0dc0c2adeae7600c638aed99795
+oid sha256:ecca73d6f016c24ec9e67e1687b94136f5bbc5b96df430ac601a3207eb26a440
 size 1341734528