Training in progress epoch 0

README.md

@@ -12,11 +12,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # knat/electra_eli5_mlm_model_kt
 
-This model is a fine-tuned version of [google/electra-small-generator](https://huggingface.co/google/electra-small-generator) on an unknown dataset.
+This model is a fine-tuned version of [knat/electra_eli5_mlm_model_kt](https://huggingface.co/knat/electra_eli5_mlm_model_kt) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 2.2236
-- Validation Loss: 2.1200
-- Epoch: 2
+- Train Loss: 2.4828
+- Validation Loss: 2.3100
+- Epoch: 0
 
 ## Model description
 
@@ -42,9 +42,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 2.4086     | 2.1770          | 0     |
-| 2.2641     | 2.1221          | 1     |
-| 2.2236     | 2.1200          | 2     |
+| 2.4828     | 2.3100          | 0     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/electra-small-generator",
+  "_name_or_path": "knat/electra_eli5_mlm_model_kt",
   "architectures": [
     "ElectraForMaskedLM"
   ],

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb44ee62a4d9b9233ecc81fd88f303048dee2f694ecc79d33c6a1c7a483fdb24
+oid sha256:81e4c04b6637bd9b58909393505086fd6176ba5105d757a43549ca98eddae825
 size 70366536