Model save

README.md

@@ -1,23 +1,11 @@
 ---
 tags:
 - generated_from_trainer
-datasets:
-- Hartunka/processed_wikitext-103-raw-v1-km-5
 metrics:
 - accuracy
 model-index:
 - name: tiny_bert_km_5_v2
-  results:
-  - task:
-      name: Masked Language Modeling
-      type: fill-mask
-    dataset:
-      name: Hartunka/processed_wikitext-103-raw-v1-km-5
-      type: Hartunka/processed_wikitext-103-raw-v1-km-5
-    metrics:
-    - name: Accuracy
-      type: accuracy
-      value: 0.15480024862971126
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -25,10 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tiny_bert_km_5_v2
 
-This model is a fine-tuned version of [](https://huggingface.co/) on the Hartunka/processed_wikitext-103-raw-v1-km-5 dataset.
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.3010
-- Accuracy: 0.1548
+- Loss: 5.5983
+- Accuracy: 0.2250
 
 ## Model description
 
@@ -60,11 +48,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step  | Validation Loss | Accuracy |
 |:-------------:|:-------:|:-----:|:---------------:|:--------:|
-| 6.4662        | 4.1982  | 10000 | 6.4854          | 0.1501   |
-| 6.1794        | 8.3963  | 20000 | 6.3069          | 0.1524   |
-| 6.0589        | 12.5945 | 30000 | 6.2953          | 0.1543   |
-| 5.9707        | 16.7926 | 40000 | 6.3172          | 0.1522   |
-| 5.9249        | 20.9908 | 50000 | 6.2770          | 0.1525   |
+| 6.435         | 4.1982  | 10000 | 6.3815          | 0.1489   |
+| 6.1783        | 8.3963  | 20000 | 6.3055          | 0.1532   |
+| 6.0524        | 12.5945 | 30000 | 6.2819          | 0.1547   |
+| 5.7467        | 16.7926 | 40000 | 5.9122          | 0.1815   |
+| 5.4323        | 20.9908 | 50000 | 5.5983          | 0.2250   |
 
 
 ### Framework versions