update model card README.md

README.md

@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [uw-madison/nystromformer-4096](https://huggingface.co/uw-madison/nystromformer-4096) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3796
-- Accuracy: 0.2773
+- Loss: 1.4537
+- Accuracy: 0.2883
 
 ## Model description
 
@@ -39,24 +39,26 @@ The following hyperparameters were used during training:
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 32
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 318  | 1.3863          | 0.2372   |
-| 1.3888        | 2.0   | 636  | 1.3858          | 0.2388   |
-| 1.3888        | 3.0   | 954  | 1.3796          | 0.2773   |
+| No log        | 0.99  | 79   | 1.3860          | 0.2467   |
+| No log        | 1.99  | 158  | 1.3853          | 0.2616   |
+| No log        | 2.99  | 237  | 1.3785          | 0.2820   |
+| No log        | 3.99  | 316  | 1.3801          | 0.2820   |
+| No log        | 4.99  | 395  | 1.4537          | 0.2883   |
 
 
 ### Framework versions
 
 - Transformers 4.26.0
 - Pytorch 1.13.1+cu116
-- Datasets 2.8.0
+- Datasets 2.9.0
 - Tokenizers 0.13.2