update model card README.md

README.md

@@ -3,7 +3,7 @@ license: mit
 tags:
 - generated_from_trainer
 datasets:
-- amazon_reviews_multi
+- dutch_social
 model-index:
 - name: xlm-roberta-base-finetuned-marc
   results: []
@@ -14,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # xlm-roberta-base-finetuned-marc
 
-This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the amazon_reviews_multi dataset.
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the dutch_social dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1299
-- Mae: 0.5619
+- Loss: 0.1992
+- Mae: 0.0532
 
 ## Model description
 
@@ -37,21 +37,19 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 1
-- eval_batch_size: 1
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 2
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Mae    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| No log        | 1.0   | 1182 | 1.1898          | 0.6    |
-| No log        | 2.0   | 2364 | 1.1299          | 0.5619 |
+| Training Loss | Epoch | Step  | Validation Loss | Mae    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 0.2824        | 1.0   | 10176 | 0.2370          | 0.0748 |
+| 0.1809        | 2.0   | 20352 | 0.1992          | 0.0532 |
 
 
 ### Framework versions