Upload TFLayoutLMForTokenClassification

README.md

@@ -4,24 +4,24 @@ base_model: microsoft/layoutlm-base-uncased
 tags:
 - generated_from_keras_callback
 model-index:
-- name: cor-c/layoutlm-funsd-tf-l
+- name: layoutlm-funsd-tf-l
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information Keras had access to. You should
 probably proofread and complete it, then remove this comment. -->
 
-# cor-c/layoutlm-funsd-tf-l
+# layoutlm-funsd-tf-l
 
 This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.3123
-- Validation Loss: 0.6608
-- Train Overall Precision: 0.7443
-- Train Overall Recall: 0.7958
-- Train Overall F1: 0.7692
-- Train Overall Accuracy: 0.8154
-- Epoch: 6
+- Train Loss: 0.2621
+- Validation Loss: 0.6925
+- Train Overall Precision: 0.7431
+- Train Overall Recall: 0.7822
+- Train Overall F1: 0.7622
+- Train Overall Accuracy: 0.8060
+- Epoch: 7
 
 ## Model description
 
@@ -54,6 +54,7 @@ The following hyperparameters were used during training:
 | 0.4482     | 0.6720          | 0.7027                  | 0.7792               | 0.7390           | 0.7917                 | 4     |
 | 0.3695     | 0.6387          | 0.7142                  | 0.7948               | 0.7523           | 0.8047                 | 5     |
 | 0.3123     | 0.6608          | 0.7443                  | 0.7958               | 0.7692           | 0.8154                 | 6     |
+| 0.2621     | 0.6925          | 0.7431                  | 0.7822               | 0.7622           | 0.8060                 | 7     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3844f6d12446bebb77e3e9eee339c3be37b08e2e813ce41d28bee6fa545caa29
+oid sha256:edbf65d245840b71538c2143fe803627762b27b9c764e8a1ce3641a383f28a23
 size 450829256