Model save

README.md

@@ -18,8 +18,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4295
-- Accuracy: 0.8925
+- Loss: 0.3208
+- Accuracy: 0.8845
+- Precision Macro: 0.8801
+- Recall Macro: 0.8750
+- F1 Macro: 0.8772
+- Precision Weighted: 0.8838
+- Recall Weighted: 0.8845
+- F1 Weighted: 0.8838
 
 ## Model description
 
@@ -44,15 +50,14 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 2
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.217         | 1.0   | 532  | 0.4129          | 0.8675   |
-| 0.176         | 2.0   | 1064 | 0.3901          | 0.888    |
-| 0.0956        | 3.0   | 1596 | 0.4295          | 0.8925   |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision Macro | Recall Macro | F1 Macro | Precision Weighted | Recall Weighted | F1 Weighted |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:------------:|:--------:|:------------------:|:---------------:|:-----------:|
+| 0.7593        | 1.0   | 532  | 0.4117          | 0.8545   | 0.8842          | 0.7863       | 0.8196   | 0.8608             | 0.8545          | 0.8519      |
+| 0.3036        | 2.0   | 1064 | 0.3208          | 0.8845   | 0.8801          | 0.8750       | 0.8772   | 0.8838             | 0.8845          | 0.8838      |
 
 
 ### Framework versions