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: 3.4533
-- Exact Match: 48.3146
-- F1: 0.0
+- Loss: 4.6998
+- Exact Match: 0.0
+- F1: 6.4735
 
 ## Model description
 
@@ -39,22 +39,20 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2.1797209639976736e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- learning_rate: 4.699689850778873e-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: 4
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Exact Match | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:-----------:|:------:|
-| No log        | 1.0   | 22   | 5.1165          | 1.1236      | 6.2440 |
-| No log        | 2.0   | 44   | 4.5043          | 28.0899     | 5.0864 |
-| No log        | 3.0   | 66   | 3.4867          | 47.1910     | 0.0    |
-| No log        | 4.0   | 88   | 3.4533          | 48.3146     | 0.0    |
+| No log        | 1.0   | 6    | 5.3004          | 0.0         | 6.3986 |
+| No log        | 2.0   | 12   | 4.6998          | 0.0         | 6.4735 |
 
 
 ### Framework versions
@@ -62,4 +60,4 @@ The following hyperparameters were used during training:
 - Transformers 4.51.2
 - Pytorch 2.6.0+cu124
 - Datasets 3.5.0
-- Tokenizers 0.21.1
+- Tokenizers 0.21.2