update model card README.md

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [antoinelouis/belgpt2](https://huggingface.co/antoinelouis/belgpt2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.7488
+- Loss: 2.5619
 
 ## Model description
 
@@ -34,20 +34,25 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3.0
+- num_epochs: 8
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 59   | 2.9197          |
-| No log        | 2.0   | 118  | 2.7798          |
-| No log        | 3.0   | 177  | 2.7488          |
+| No log        | 1.0   | 26   | 2.9939          |
+| No log        | 2.0   | 52   | 2.7641          |
+| No log        | 3.0   | 78   | 2.6621          |
+| No log        | 4.0   | 104  | 2.6129          |
+| No log        | 5.0   | 130  | 2.5897          |
+| No log        | 6.0   | 156  | 2.5722          |
+| No log        | 7.0   | 182  | 2.5630          |
+| No log        | 8.0   | 208  | 2.5619          |
 
 
 ### Framework versions