Upload TFBertForSequenceClassification

README.md

@@ -3,17 +3,9 @@ license: apache-2.0
 base_model: bert-base-uncased
 tags:
 - generated_from_keras_callback
-- really-cool
 model-index:
 - name: bert-base-uncased-finetuned-glue-sst2
   results: []
-datasets:
-- glue
-language:
-- en
-metrics:
-- accuracy
-pipeline_tag: text-classification
 ---
 
 <!-- This model card has been generated automatically according to the information Keras had access to. You should
@@ -21,19 +13,21 @@ probably proofread and complete it, then remove this comment. -->
 
 # bert-base-uncased-finetuned-glue-sst2
 
-Use for **sentiment analysis**. Labels: `positive`, `negative`
+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:
 
-This model is a fine-tuned version of the [bert-base-uncased](https://huggingface.co/bert-base-uncased) model, fine-tuned on a subset of the [glue sst2 dataset](https://huggingface.co/datasets/glue/viewer/sst2). It achieves `91.74%` accuracy on the validation dataset. 
 
 ## Model description
 
-The `bert-base-uncased` model is a pretrained English language model which has learned a bidirectional representation through Masked Language Modeling (MLM).
+More information needed
 
-The `bert-base-uncased-finetuned-glue-sst2` adds a 2-class classification head to `bert-base-uncased`. It is then fine-tuned for **sentiment analysis** on the [glue sst2 dataset](https://huggingface.co/datasets/glue/viewer/sst2).
+## Intended uses & limitations
+
+More information needed
 
 ## Training and evaluation data
 
-This model was only trained on 10000 samples, while the entire glue sst2 training set includes 67349 examples. This was done mainly to decrease training time.
+More information needed
 
 ## Training procedure
 
@@ -45,12 +39,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-- Accuracy (training): `94.08%`
-- Accuracy (validation): `91.74%`
+
 
 ### Framework versions
 
 - Transformers 4.35.2
 - TensorFlow 2.15.0
 - Datasets 2.16.1
-- Tokenizers 0.15.0
+- Tokenizers 0.15.0

config.json

@@ -10,14 +10,14 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "negative": 0,
-    "positive": 1
+    "0": "negative",
+    "1": "positive"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "0": "negative",
-    "1": "positive"
+    "negative": 0,
+    "positive": 1
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a30c9dd440db01dc056bb5a7e68c619a17ad10082d1e0de294d1bb53cf227f0f
+oid sha256:6aba084d763a2ae05810d8bcca305dce000e670ffee5f1dbfba402bf2efa4fa7
 size 438223128