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: 3.4886
-- Exact Match: 48.3146
-- F1: 0.0
+- Loss: 3.9533
+- Exact Match: 44.9438
+- F1: 0.4406
 
 ## Model description
 
@@ -39,23 +39,22 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2.356216203001653e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 1.7488487465623482e-05
+- train_batch_size: 8
+- eval_batch_size: 8
 - 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: 5
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Exact Match | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:-----------:|:------:|
-| No log        | 1.0   | 16   | 4.9292          | 38.2022     | 2.9401 |
-| No log        | 2.0   | 32   | 4.1936          | 48.3146     | 1.1609 |
-| No log        | 3.0   | 48   | 3.8582          | 48.3146     | 0.0    |
-| No log        | 4.0   | 64   | 3.6638          | 48.3146     | 0.8232 |
-| No log        | 5.0   | 80   | 3.4886          | 48.3146     | 0.0    |
+| No log        | 1.0   | 22   | 5.4708          | 19.1011     | 3.7917 |
+| No log        | 2.0   | 44   | 4.4491          | 48.3146     | 0.0    |
+| No log        | 3.0   | 66   | 4.0419          | 47.1910     | 0.0    |
+| No log        | 4.0   | 88   | 3.9533          | 44.9438     | 0.4406 |
 
 
 ### Framework versions