Training complete

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [vinai/bartpho-syllable](https://huggingface.co/vinai/bartpho-syllable) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2603
-- Sacrebleu: 13.8971
+- Loss: 0.0561
+- Sacrebleu: 22.9297
 
 ## Model description
 
@@ -38,27 +38,25 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 20
-- eval_batch_size: 20
+- train_batch_size: 12
+- eval_batch_size: 12
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 80
+- total_train_batch_size: 48
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 8
+- num_epochs: 5
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|
-| No log        | 0.96  | 12   | 0.7531          | 10.4358   |
-| No log        | 2.0   | 25   | 0.7129          | 10.4963   |
-| No log        | 2.96  | 37   | 0.4248          | 11.1595   |
-| No log        | 4.0   | 50   | 0.3501          | 11.6392   |
-| No log        | 4.96  | 62   | 0.3043          | 12.6744   |
-| No log        | 6.0   | 75   | 0.2758          | 13.4012   |
-| No log        | 6.96  | 87   | 0.2629          | 13.7842   |
-| No log        | 7.68  | 96   | 0.2603          | 13.8971   |
+| No log        | 1.0   | 104  | 0.0988          | 17.3540   |
+| No log        | 2.0   | 208  | 0.0661          | 21.5130   |
+| No log        | 3.0   | 312  | 0.0593          | 22.4272   |
+| No log        | 4.0   | 416  | 0.0564          | 22.8821   |
+| No log        | 5.0   | 520  | 0.0561          | 22.9297   |
 
 
 ### Framework versions