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: 3.0320
-- Exact Match: 44.4444
-- F1: 0.8595
+- Loss: 3.6571
+- Exact Match: 41.5730
+- F1: 0.6310
 
 ## Model description
 
@@ -39,9 +39,9 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2.7314506856045412e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 1.5101664377049603e-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
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Exact Match | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:-----------:|:------:|
-| No log        | 1.0   | 33   | 4.1291          | 44.8413     | 0.0    |
-| No log        | 2.0   | 66   | 3.3262          | 44.8413     | 0.0    |
-| No log        | 3.0   | 99   | 3.1032          | 44.8413     | 0.0    |
-| No log        | 4.0   | 132  | 3.0320          | 44.4444     | 0.8595 |
+| No log        | 1.0   | 32   | 4.8737          | 10.1124     | 4.5405 |
+| No log        | 2.0   | 64   | 4.0712          | 13.4831     | 2.6494 |
+| No log        | 3.0   | 96   | 3.7312          | 48.3146     | 0.0    |
+| No log        | 4.0   | 128  | 3.6571          | 41.5730     | 0.6310 |
 
 
 ### Framework versions