Training in progress epoch 0

README.md

@@ -14,10 +14,10 @@ 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: 0.4732
-- Validation Loss: 0.4255
-- Train Accuracy: 0.9103
-- Epoch: 1
+- Train Loss: 0.9061
+- Validation Loss: 0.6146
+- Train Accuracy: 0.8184
+- Epoch: 0
 
 ## Model description
 
@@ -43,13 +43,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.9479     | 0.5602          | 0.8767         | 0     |
-| 0.4732     | 0.4255          | 0.9103         | 1     |
+| 0.9061     | 0.6146          | 0.8184         | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.29.2
+- Transformers 4.30.1
 - TensorFlow 2.12.0
 - Datasets 2.12.0
 - Tokenizers 0.13.3

config.json

@@ -30,6 +30,6 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "transformers_version": "4.29.2",
+  "transformers_version": "4.30.1",
   "vocab_size": 30522
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55842279d931de2bf0232dc3c442a38665612333a77e8d2c022409e7ecb26df9
-size 267957952
+oid sha256:3221ee70e5b93794c9024903d6a3f37a9fb9ab8acea5e14efcc22ccfc1e3cb6d
+size 267961288