Model save

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.4455
-- Exact Match: 31.4607
-- F1: 0.3958
+- Loss: 5.5450
+- Exact Match: 22.4719
+- F1: 2.9603
 
 ## Model description
 
@@ -39,21 +39,20 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3.338177248512558e-05
+- learning_rate: 2.3044973559870577e-05
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Exact Match | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:-----------:|:------:|
-| No log        | 1.0   | 8    | 5.2961          | 17.9775     | 3.9016 |
-| No log        | 2.0   | 16   | 4.6305          | 11.2360     | 3.9679 |
-| No log        | 3.0   | 24   | 4.4455          | 31.4607     | 0.3958 |
+| No log        | 1.0   | 6    | 5.8290          | 15.7303     | 5.4173 |
+| No log        | 2.0   | 12   | 5.5450          | 22.4719     | 2.9603 |
 
 
 ### Framework versions