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: 5.9685
-- Exact Match: 17.9775
-- F1: 5.3481
+- Loss: 4.7829
+- Exact Match: 19.1011
+- F1: 3.7297
 
 ## Model description
 
@@ -39,20 +39,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 6.091765812519654e-06
+- learning_rate: 2.006663988844745e-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: 2
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Exact Match | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:-----------:|:------:|
-| No log        | 1.0   | 6    | 5.9763          | 20.2247     | 5.0606 |
-| No log        | 2.0   | 12   | 5.9685          | 17.9775     | 5.3481 |
+| No log        | 1.0   | 6    | 5.6706          | 4.4944      | 5.7913 |
+| No log        | 2.0   | 12   | 5.3199          | 32.5843     | 1.9915 |
+| No log        | 3.0   | 18   | 4.9960          | 13.4831     | 4.2031 |
+| No log        | 4.0   | 24   | 4.9204          | 37.0787     | 0.1673 |
+| No log        | 5.0   | 30   | 4.7829          | 19.1011     | 3.7297 |
 
 
 ### Framework versions