Training in progress epoch 0

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: 0.0101
-- Train Sparse Categorical Accuracy: 0.9972
-- Validation Loss: 0.0110
-- Validation Sparse Categorical Accuracy: 0.9974
-- Epoch: 3
+- Train Loss: 0.0541
+- Train Sparse Categorical Accuracy: 0.9841
+- Validation Loss: 0.0250
+- Validation Sparse Categorical Accuracy: 0.9929
+- Epoch: 0
 
 ## Model description
 
@@ -44,10 +44,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
 |:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
-| 0.0485     | 0.9862                            | 0.0197          | 0.9952                                 | 0     |
-| 0.0180     | 0.9953                            | 0.0150          | 0.9962                                 | 1     |
-| 0.0126     | 0.9966                            | 0.0115          | 0.9970                                 | 2     |
-| 0.0101     | 0.9972                            | 0.0110          | 0.9974                                 | 3     |
+| 0.0541     | 0.9841                            | 0.0250          | 0.9929                                 | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:035ec4db62e740e6b32edf0ea05cdc626e0a2b4dec2b104db23404b1e1c17198
+oid sha256:7df48dccd7a2f6c42f8dd511db888651b5ed8182b0972a06c26d9391e6731547
 size 51151160