End of training

README.md

@@ -1,6 +1,6 @@
 ---
 library_name: transformers
-base_model: microsoft/infoxlm-large
+base_model: tringuyen-uit/MRC_ER_InfoXLM-large_syl_DSC
 tags:
 - generated_from_trainer
 metrics:
@@ -15,11 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # MRC_ER_InfoXLM-large_syl_DSC
 
-This model is a fine-tuned version of [microsoft/infoxlm-large](https://huggingface.co/microsoft/infoxlm-large) on the None dataset.
+This model is a fine-tuned version of [tringuyen-uit/MRC_ER_InfoXLM-large_syl_DSC](https://huggingface.co/tringuyen-uit/MRC_ER_InfoXLM-large_syl_DSC) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9209
-- Exact Match: 0.7105
-- F1: 0.8665
+- Loss: 0.9789
+- Exact Match: 0.7016
+- F1: 0.8574
 
 ## Model description
 
@@ -44,15 +44,14 @@ 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: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Exact Match | F1     |
 |:-------------:|:-----:|:-----:|:---------------:|:-----------:|:------:|
-| 0.9362        | 1.0   | 12728 | 0.8115          | 0.6279      | 0.7988 |
-| 0.7449        | 2.0   | 25456 | 0.9053          | 0.6728      | 0.8369 |
-| 0.7071        | 3.0   | 38184 | 0.9209          | 0.7105      | 0.8665 |
+| 0.6848        | 1.0   | 12728 | 0.9842          | 0.6596      | 0.8277 |
+| 0.6025        | 2.0   | 25456 | 0.9789          | 0.7016      | 0.8574 |
 
 
 ### Framework versions