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: 4.9370
-- Exact Match: 32.5843
-- F1: 4.3078
+- Loss: 5.1793
+- Exact Match: 39.3258
+- F1: 1.6839
 
 ## Model description
 
@@ -39,7 +39,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2.0906870238250747e-05
+- learning_rate: 1.5992536419295564e-05
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Exact Match | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:-----------:|:------:|
-| No log        | 1.0   | 6    | 5.4465          | 7.8652      | 4.7592 |
-| No log        | 2.0   | 12   | 5.0066          | 16.8539     | 3.6640 |
-| No log        | 3.0   | 18   | 5.0060          | 29.2135     | 4.4112 |
-| No log        | 4.0   | 24   | 4.9370          | 32.5843     | 4.3078 |
+| No log        | 1.0   | 6    | 5.4185          | 46.0674     | 0.0    |
+| No log        | 2.0   | 12   | 5.0475          | 43.8202     | 0.4957 |
+| No log        | 3.0   | 18   | 5.2731          | 41.5730     | 1.5512 |
+| No log        | 4.0   | 24   | 5.1793          | 39.3258     | 1.6839 |
 
 
 ### Framework versions