Model save

README.md

@@ -1,28 +1,13 @@
 ---
-language:
-- en
 license: apache-2.0
 base_model: google/fnet-base
 tags:
 - generated_from_trainer
-datasets:
-- glue
 metrics:
 - matthews_correlation
 model-index:
 - name: fnet-base-finetuned-cola
-  results:
-  - task:
-      name: Text Classification
-      type: text-classification
-    dataset:
-      name: GLUE COLA
-      type: glue
-      args: cola
-    metrics:
-    - name: Matthews Correlation
-      type: matthews_correlation
-      value: 0.3262988329908328
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # fnet-base-finetuned-cola
 
-This model is a fine-tuned version of [google/fnet-base](https://huggingface.co/google/fnet-base) on the GLUE COLA dataset.
+This model is a fine-tuned version of [google/fnet-base](https://huggingface.co/google/fnet-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5648
-- Matthews Correlation: 0.3263
+- Loss: 0.6476
+- Matthews Correlation: 0.3934
 
 ## Model description
 
@@ -58,15 +43,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3.0
+- num_epochs: 5.0
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.6101        | 1.0   | 268  | 0.6032          | 0.1346               |
-| 0.5325        | 2.0   | 536  | 0.5451          | 0.3135               |
-| 0.428         | 3.0   | 804  | 0.5648          | 0.3263               |
+| 0.61          | 1.0   | 268  | 0.5818          | 0.1606               |
+| 0.5265        | 2.0   | 536  | 0.5489          | 0.3415               |
+| 0.4161        | 3.0   | 804  | 0.5454          | 0.3451               |
+| 0.3324        | 4.0   | 1072 | 0.5746          | 0.3869               |
+| 0.2657        | 5.0   | 1340 | 0.6476          | 0.3934               |
 
 
 ### Framework versions