End of training

README.md

@@ -1,11 +1,11 @@
 ---
-base_model: IAmSkyDra/BARTBana_v4
 library_name: transformers
 license: mit
-metrics:
-- sacrebleu
+base_model: IAmSkyDra/BARTBana_v4
 tags:
 - generated_from_trainer
+metrics:
+- sacrebleu
 model-index:
 - name: BARTBana_Translation_ReplaceSymWord_v0
   results: []
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [IAmSkyDra/BARTBana_v4](https://huggingface.co/IAmSkyDra/BARTBana_v4) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0261
-- Sacrebleu: 20.4115
+- Loss: 0.0861
+- Sacrebleu: 15.3102
 
 ## Model description
 
@@ -44,23 +44,21 @@ The following hyperparameters were used during training:
 - 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
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Sacrebleu |
 |:-------------:|:-----:|:-----:|:---------------:|:---------:|
-| 0.2981        | 1.0   | 7111  | 0.2214          | 9.2406    |
-| 0.1405        | 2.0   | 14222 | 0.0835          | 15.4247   |
-| 0.0822        | 3.0   | 21333 | 0.0436          | 18.4992   |
-| 0.0591        | 4.0   | 28444 | 0.0299          | 19.9525   |
-| 0.0498        | 5.0   | 35555 | 0.0261          | 20.4115   |
+| 0.3205        | 1.0   | 7111  | 0.2434          | 8.5066    |
+| 0.1779        | 2.0   | 14222 | 0.1138          | 13.6308   |
+| 0.1384        | 3.0   | 21333 | 0.0861          | 15.3102   |
 
 
 ### Framework versions
 
-- Transformers 4.48.1
-- Pytorch 2.5.1+cu124
+- Transformers 4.48.2
+- Pytorch 2.6.0+cu124
 - Datasets 3.2.0
 - Tokenizers 0.21.0