Training in progress epoch 0

README.md

@@ -12,9 +12,9 @@ probably proofread and complete it, then remove this comment. -->
 
 # ogtega/tweet-toxicity-classifier
 
-This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.7899
+- Train Loss: 1.8598
 - Epoch: 0
 
 ## Model description
@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Epoch |
 |:----------:|:-----:|
-| 1.7899     | 0     |
+| 1.8598     | 0     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-base-cased",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -38,5 +38,5 @@
   "transformers_version": "4.28.1",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 28996
+  "vocab_size": 30522
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d0aed1d021d09063cb01e16ed301a482a55fc31ecd47dbbd1293327be97aad2
-size 433547560
+oid sha256:e548e850b95e0c18e57d3d2840151844a33cebfb992bc9f2e78c7df9189d697c
+size 438235432

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": false,
+  "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",