namngo
/

vipubmed-deberta-xsmall-finetuned-squad

Question Answering

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

namngo commited on Aug 17, 2023

Commit

c76ab7b

•

1 Parent(s): 276599c

update model card README.md

Files changed (1) hide show

README.md +16 -16

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [manhtt-079/vipubmed-deberta-xsmall](https://huggingface.co/manhtt-079/vipubmed-deberta-xsmall) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0986
 ## Model description
@@ -33,9 +33,9 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
-- train_batch_size: 32
-- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -44,18 +44,18 @@ The following hyperparameters were used during training:
 ### Training results
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 4.3053        | 1.0   | 845  | 3.3807          |
-| 3.0627        | 2.0   | 1690 | 2.7710          |
-| 2.2496        | 3.0   | 2535 | 2.6862          |
-| 2.0757        | 4.0   | 3380 | 2.5335          |
-| 1.8615        | 5.0   | 4225 | 2.2315          |
-| 1.7144        | 6.0   | 5070 | 2.3905          |
-| 1.6598        | 7.0   | 5915 | 2.1928          |
-| 1.5843        | 8.0   | 6760 | 2.1073          |
-| 1.5172        | 9.0   | 7605 | 2.0659          |
-| 1.4915        | 10.0  | 8450 | 2.0986          |
 ### Framework versions

 This model is a fine-tuned version of [manhtt-079/vipubmed-deberta-xsmall](https://huggingface.co/manhtt-079/vipubmed-deberta-xsmall) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 2.4768
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 6e-05
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 ### Training results
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 2.6181        | 1.0   | 1196  | 1.9617          |
+| 1.6439        | 2.0   | 2392  | 1.5840          |
+| 1.2607        | 3.0   | 3588  | 1.6354          |
+| 1.0223        | 4.0   | 4784  | 1.6411          |
+| 0.7925        | 5.0   | 5980  | 1.7369          |
+| 0.6184        | 6.0   | 7176  | 1.8626          |
+| 0.5019        | 7.0   | 8372  | 2.1214          |
+| 0.4125        | 8.0   | 9568  | 2.2120          |
+| 0.321         | 9.0   | 10764 | 2.3238          |
+| 0.2899        | 10.0  | 11960 | 2.4768          |
 ### Framework versions