Upload TFDistilBertForSequenceClassification

README.md

@@ -14,11 +14,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.2273
-- Train Accuracy: 0.9333
-- Validation Loss: 1.5347
-- Validation Accuracy: 0.6304
-- Epoch: 5
+- Train Loss: 1.0219
+- Train Accuracy: 0.6909
+- Validation Loss: 1.2971
+- Validation Accuracy: 0.6174
+- Epoch: 2
 
 ## Model description
 
@@ -44,12 +44,9 @@ The following hyperparameters were used during training:
 
 | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| 1.5170     | 0.4897         | 1.3276          | 0.6000              | 0     |
-| 1.2290     | 0.6024         | 1.1932          | 0.6304              | 1     |
-| 0.9283     | 0.7103         | 1.1967          | 0.6000              | 2     |
-| 0.5667     | 0.8242         | 1.4213          | 0.5130              | 3     |
-| 0.3583     | 0.8861         | 1.3406          | 0.6261              | 4     |
-| 0.2273     | 0.9333         | 1.5347          | 0.6304              | 5     |
+| 1.5339     | 0.4752         | 1.3023          | 0.5652              | 0     |
+| 1.2663     | 0.6012         | 1.2350          | 0.5870              | 1     |
+| 1.0219     | 0.6909         | 1.2971          | 0.6174              | 2     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c059675693862572d9d7008dcfaf51f915aa9a0965cf21c93a511f9a20113ef
+oid sha256:d2fffdead9a921557111881e49e2a6f9013d769423f907a87222251d6045857e
 size 267977896