update model card README.md

README.md

@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [aubmindlab/aragpt2-mega-detector-long](https://huggingface.co/aubmindlab/aragpt2-mega-detector-long) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6113
-- Macro F1: 0.7072
-- Accuracy: 0.7175
-- Precision: 0.7090
-- Recall: 0.7059
+- Loss: 0.5249
+- Macro F1: 0.7536
+- Accuracy: 0.7626
+- Precision: 0.7563
+- Recall: 0.7517
 
 ## Model description
 
@@ -41,28 +41,28 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 25
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 32
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Macro F1 | Accuracy | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|:------:|
-| 0.5809        | 1.0   | 1597 | 0.5598          | 0.6997   | 0.7069   | 0.6990    | 0.7006 |
-| 0.4958        | 2.0   | 3194 | 0.5369          | 0.7012   | 0.7224   | 0.7212    | 0.6973 |
-| 0.4376        | 3.0   | 4791 | 0.5769          | 0.7042   | 0.7083   | 0.7036    | 0.7085 |
-| 0.3993        | 4.0   | 6388 | 0.6113          | 0.7072   | 0.7175   | 0.7090    | 0.7059 |
+| 0.588         | 1.0   | 798  | 0.5131          | 0.7235   | 0.7384   | 0.7341    | 0.7197 |
+| 0.462         | 2.0   | 1596 | 0.5112          | 0.7408   | 0.7574   | 0.7587    | 0.7357 |
+| 0.4034        | 3.0   | 2394 | 0.5249          | 0.7536   | 0.7626   | 0.7563    | 0.7517 |
+| 0.3234        | 4.0   | 3192 | 0.5967          | 0.7524   | 0.7585   | 0.7516    | 0.7534 |
 
 
 ### Framework versions
 
-- Transformers 4.12.2
+- Transformers 4.20.1
 - Pytorch 1.11.0
 - Datasets 2.1.0
-- Tokenizers 0.10.3
+- Tokenizers 0.12.1