Upload TFBertForTokenClassification

README.md

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0023
-- Validation Loss: 0.0058
-- Epoch: 4
+- Train Loss: 0.0055
+- Validation Loss: 0.0050
+- Epoch: 2
 
 ## Model description
 
@@ -42,16 +42,14 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.0665     | 0.0161          | 0     |
-| 0.0116     | 0.0083          | 1     |
-| 0.0062     | 0.0075          | 2     |
-| 0.0036     | 0.0059          | 3     |
-| 0.0023     | 0.0058          | 4     |
+| 0.0833     | 0.0156          | 0     |
+| 0.0100     | 0.0060          | 1     |
+| 0.0055     | 0.0050          | 2     |
 
 
 ### Framework versions
 
-- Transformers 4.25.1
+- Transformers 4.26.1
 - TensorFlow 2.9.2
-- Datasets 2.8.0
+- Datasets 2.9.0
 - Tokenizers 0.13.2

config.json

@@ -60,7 +60,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.25.1",
+  "transformers_version": "4.26.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 28996

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34c35e89c69c68dc9ca68cd92f4d9e69a5cd1f3f4b14d8b493b46afd6bc29a9b
+oid sha256:04310e25aef543ec37ec6057472c06c618c596c6cec0cc9065cbd2d2f35b94ca
 size 431222868