update model card README.md

README.md

@@ -1,6 +1,4 @@
 ---
-language:
-- distilbert-science-exam-sm
 license: apache-2.0
 base_model: distilbert-base-cased
 tags:
@@ -19,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4993
-- Accuracy: 0.6
+- Loss: 1.2390
+- Accuracy: 0.7
 
 ## Model description
 
@@ -43,8 +41,8 @@ The following hyperparameters were used during training:
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 16
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 3
@@ -53,9 +51,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 12   | 1.5887          | 0.6      |
-| No log        | 2.0   | 24   | 1.5421          | 0.6      |
-| No log        | 3.0   | 36   | 1.4993          | 0.6      |
+| No log        | 1.0   | 6    | 1.0428          | 0.5      |
+| No log        | 2.0   | 12   | 1.3253          | 0.5      |
+| No log        | 3.0   | 18   | 1.2390          | 0.7      |
 
 
 ### Framework versions