Training in progress epoch 0

README.md

@@ -15,10 +15,10 @@ 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: 0.6735
-- Validation Loss: 0.6778
-- Train Accuracy: 0.6042
-- Epoch: 1
+- Train Loss: 0.6159
+- Validation Loss: 0.6435
+- Train Accuracy: 0.6490
+- Epoch: 0
 
 ## Model description
 
@@ -44,8 +44,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.6905     | 0.6874          | 0.5369         | 0     |
-| 0.6735     | 0.6778          | 0.6042         | 1     |
+| 0.6159     | 0.6435          | 0.6490         | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f98cea7ec7f97582e80c7ab9ebfcfa352ec8b0482f1f1d094bb567bd9ce9a5f
+oid sha256:d57a520f6b63516457012d8f72419e5802d50364ee31e2992fbd46224d418b3a
 size 267955144

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {