Training in progress epoch 0

README.md

@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
 
 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: 0.8380
-- Validation Loss: 0.5196
-- Epoch: 5
+- Train Loss: 8.0542
+- Validation Loss: 7.3497
+- Epoch: 0
 
 ## Model description
 
@@ -43,12 +43,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 7.0548     | 5.2961          | 0     |
-| 4.5869     | 3.8365          | 1     |
-| 3.3215     | 2.7372          | 2     |
-| 2.2476     | 1.5765          | 3     |
-| 1.3636     | 0.8208          | 4     |
-| 0.8380     | 0.5196          | 5     |
+| 8.0542     | 7.3497          | 0     |
 
 
 ### Framework versions

config.json

@@ -11,6 +11,7 @@
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
+  "is_decoder": true,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d80ec782892f37dc9bead6bad8b237632a55992035f94fa1523ab771e55ad82
+oid sha256:535c280b2518d5d4c96eec45094d5f4016d4a25a347a1a6f73eee57cb963746d
 size 533687616