kientran/viderberta_for_VN_TourQA_v2

README.md

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7850
+- Loss: 1.2816
 
 ## Model description
 
@@ -43,23 +43,23 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 3.1467        | 1.0   | 898  | 2.5506          |
-| 2.5202        | 2.0   | 1796 | 2.3433          |
-| 2.2756        | 3.0   | 2694 | 2.1759          |
-| 2.1163        | 4.0   | 3592 | 2.0219          |
-| 1.9712        | 5.0   | 4490 | 1.9532          |
-| 1.8613        | 6.0   | 5388 | 1.9072          |
-| 1.7525        | 7.0   | 6286 | 1.8221          |
-| 1.6517        | 8.0   | 7184 | 1.7949          |
-| 1.5768        | 9.0   | 8082 | 1.7926          |
-| 1.5367        | 10.0  | 8980 | 1.7850          |
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 2.2435        | 1.0   | 1369  | 1.9326          |
+| 2.038         | 2.0   | 2738  | 1.8181          |
+| 1.8689        | 3.0   | 4107  | 1.6199          |
+| 1.7463        | 4.0   | 5476  | 1.5103          |
+| 1.5708        | 5.0   | 6845  | 1.4584          |
+| 1.4138        | 6.0   | 8214  | 1.4221          |
+| 1.3471        | 7.0   | 9583  | 1.3381          |
+| 1.2514        | 8.0   | 10952 | 1.2927          |
+| 1.2016        | 9.0   | 12321 | 1.2848          |
+| 1.1532        | 10.0  | 13690 | 1.2816          |
 
 
 ### Framework versions
 
 - Transformers 4.42.4
-- Pytorch 2.3.1+cu121
-- Datasets 2.20.0
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
 - Tokenizers 0.19.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/content/drive/MyDrive/KLTN/results/tuned_Videberta_base_big",
+  "_name_or_path": "/content/drive/MyDrive/KLTN/results/tuned_Videberta_base_after_big",
   "architectures": [
     "DebertaV2ForQuestionAnswering"
   ],

log/events.out.tfevents.1725107129.562bc6fc5216.3065.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cef0517d1fc0ac2b5aef27835d680031ffcc8b70aff66dc6fe99b4a28af05786
+size 14062

log/events.out.tfevents.1725111925.562bc6fc5216.3065.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd8fb011ff363af18c8299374e34f8628c5ab9be37536a38e095d03c06b61146
+size 359

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd684ae6cfa05a9c6805a69b414a3617a27db2cd6fd0b4193ef0a339a70a7f74
+oid sha256:32542fa1b144f900f0bee14dcf1b1c682f830ad7e165391d0745090fd91b83c7
 size 735049552