Training in progress epoch 3

README.md

@@ -14,11 +14,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/xtremedistil-l6-h256-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h256-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0158
-- Train Sparse Categorical Accuracy: 0.9953
-- Validation Loss: 0.0161
-- Validation Sparse Categorical Accuracy: 0.9953
-- Epoch: 2
+- Train Loss: 0.0126
+- Train Sparse Categorical Accuracy: 0.9961
+- Validation Loss: 0.0148
+- Validation Sparse Categorical Accuracy: 0.9955
+- Epoch: 3
 
 ## Model description
 
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 0.0541     | 0.9841                            | 0.0250          | 0.9929                                 | 0     |
 | 0.0223     | 0.9936                            | 0.0186          | 0.9947                                 | 1     |
 | 0.0158     | 0.9953                            | 0.0161          | 0.9953                                 | 2     |
+| 0.0126     | 0.9961                            | 0.0148          | 0.9955                                 | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df6f65701181a9615615952f4835f7c24473ca00bd3ff0167c11d178078bdfcb
+oid sha256:6224c452e1964bffb5fc48f739c1936cc488a422760f84d9e177c5bbbd3b5332
 size 51151160