update model card README.md

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8059
-- Accuracy: 0.586
+- Loss: 1.1661
+- Accuracy: 0.6440
 
 ## Model description
 
@@ -37,8 +37,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 64
-- eval_batch_size: 8
+- train_batch_size: 256
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.8012        | 1.0   | 16   | 1.8824          | 0.584    |
-| 1.4111        | 2.0   | 32   | 1.8159          | 0.568    |
-| 1.3755        | 3.0   | 48   | 1.8059          | 0.586    |
+| 1.3877        | 1.0   | 247  | 1.2393          | 0.6278   |
+| 1.1172        | 2.0   | 494  | 1.1769          | 0.6415   |
+| 0.9312        | 3.0   | 741  | 1.1661          | 0.6440   |
 
 
 ### Framework versions