Training in progress epoch 3

README.md

@@ -14,13 +14,13 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.7253
-- Train End Logits Accuracy: 0.7637
-- Train Start Logits Accuracy: 0.7515
-- Validation Loss: 0.9841
-- Validation End Logits Accuracy: 0.7182
-- Validation Start Logits Accuracy: 0.7124
-- Epoch: 2
+- Train Loss: 0.5678
+- Train End Logits Accuracy: 0.8090
+- Train Start Logits Accuracy: 0.7986
+- Validation Loss: 1.0107
+- Validation End Logits Accuracy: 0.7260
+- Validation Start Logits Accuracy: 0.7194
+- Epoch: 3
 
 ## Model description
 
@@ -49,6 +49,7 @@ The following hyperparameters were used during training:
 | 1.4847     | 0.5934                    | 0.5787                      | 1.1159          | 0.6724                         | 0.6590                           | 0     |
 | 0.9507     | 0.7042                    | 0.6909                      | 1.0094          | 0.6973                         | 0.6875                           | 1     |
 | 0.7253     | 0.7637                    | 0.7515                      | 0.9841          | 0.7182                         | 0.7124                           | 2     |
+| 0.5678     | 0.8090                    | 0.7986                      | 1.0107          | 0.7260                         | 0.7194                           | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23296e48551fe92c257b757541436354de724ce56435cfd8d0500d395fc14fe
+oid sha256:138ec47707e33acda5be5eba771138869197d4defd5486f41888f893061db2de
 size 260895720