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: 4.7697
-- Exact Match: 41.5730
-- F1: 1.2761
+- Loss: 5.0418
+- Exact Match: 21.3483
+- F1: 5.8917
 
 ## Model description
 
@@ -39,23 +39,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2.2261464858561894e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- learning_rate: 3.109345114384633e-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: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Exact Match | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:-----------:|:------:|
-| No log        | 1.0   | 6    | 5.7375          | 30.3371     | 2.8248 |
-| No log        | 2.0   | 12   | 5.2940          | 23.5955     | 3.9492 |
-| No log        | 3.0   | 18   | 5.0891          | 41.5730     | 0.1310 |
-| No log        | 4.0   | 24   | 5.0105          | 47.1910     | 0.4682 |
-| No log        | 5.0   | 30   | 4.7697          | 41.5730     | 1.2761 |
+| No log        | 1.0   | 22   | 5.3859          | 12.3596     | 7.2183 |
+| No log        | 2.0   | 44   | 5.1121          | 10.1124     | 6.2278 |
+| No log        | 3.0   | 66   | 5.0418          | 21.3483     | 5.8917 |
 
 
 ### Framework versions