End of training

README.md

@@ -14,13 +14,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [vinai/bartpho-word-base](https://huggingface.co/vinai/bartpho-word-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0130
-- F1 Micro: 0.7393
-- Recall Micro: 0.6664
-- Precision Micro: 0.8303
-- F1 Macro: 0.1848
-- Recall Macro: 0.1784
-- Precision Macro: 0.1936
+- Loss: 0.0125
+- F1 Micro: 0.7420
+- Recall Micro: 0.6752
+- Precision Micro: 0.8234
+- F1 Macro: 0.1574
+- Recall Macro: 0.1447
+- Precision Macro: 0.1833
 
 ## Model description
 
@@ -45,16 +45,14 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1 Micro | Recall Micro | Precision Micro | F1 Macro | Recall Macro | Precision Macro |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------------:|:---------------:|:--------:|:------------:|:---------------:|
-| 0.0118        | 1.0   | 1492 | 0.0132          | 0.7380   | 0.6619       | 0.8340          | 0.1729   | 0.1706       | 0.1962          |
-| 0.0083        | 2.0   | 2984 | 0.0123          | 0.7412   | 0.6608       | 0.8438          | 0.1776   | 0.1630       | 0.1995          |
-| 0.0054        | 3.0   | 4476 | 0.0130          | 0.7393   | 0.6664       | 0.8303          | 0.1848   | 0.1784       | 0.1936          |
+| 0.018         | 1.0   | 1492 | 0.0125          | 0.7420   | 0.6752       | 0.8234          | 0.1574   | 0.1447       | 0.1833          |
 
 
 ### Framework versions