Upload TFBertForMaskedLM

README.md

@@ -1,6 +1,6 @@
 ---
-base_model: google-bert/bert-base-german-cased
 license: mit
+base_model: google-bert/bert-base-german-cased
 tags:
 - generated_from_keras_callback
 model-index:
@@ -15,8 +15,8 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-bert/bert-base-german-cased](https://huggingface.co/google-bert/bert-base-german-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 2.4288
-- Epoch: 0
+- Train Loss: 1.2900
+- Epoch: 9
 
 ## Model description
 
@@ -42,7 +42,16 @@ The following hyperparameters were used during training:
 
 | Train Loss | Epoch |
 |:----------:|:-----:|
-| 2.4288     | 0     |
+| 2.4250     | 0     |
+| 1.3110     | 1     |
+| 1.3098     | 2     |
+| 1.3043     | 3     |
+| 1.3020     | 4     |
+| 1.3002     | 5     |
+| 1.2968     | 6     |
+| 1.2929     | 7     |
+| 1.2927     | 8     |
+| 1.2900     | 9     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbb1acd14f1bc9bb1b7851603c3a816f0ce88399464779f14697461c49d7e06b
+oid sha256:2848689bc738e4211f36ea00acce577836c1d84ff14b8dc909b426a52ce7f04e
 size 530478360