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 16, 2023

Commit

6d5a96b

•

1 Parent(s): 819942b

update model card README.md

Files changed (1) hide show

README.md +15 -15

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: 2.4105
 ## Model description
@@ -34,8 +34,8 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 5e-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
@@ -44,18 +44,18 @@ The following hyperparameters were used during training:
 ### Training results
-| Training Loss | Epoch | Step  | Validation Loss |
-|:-------------:|:-----:|:-----:|:---------------:|
-| 2.1456        | 1.0   | 1615  | 1.9540          |
-| 1.5495        | 2.0   | 3230  | 1.5950          |
-| 1.2336        | 3.0   | 4845  | 1.5831          |
-| 0.9791        | 4.0   | 6460  | 1.6567          |
-| 0.7751        | 5.0   | 8075  | 1.6597          |
-| 0.642         | 6.0   | 9690  | 1.8969          |
-| 0.5279        | 7.0   | 11305 | 2.0252          |
-| 0.4283        | 8.0   | 12920 | 2.1866          |
-| 0.3665        | 9.0   | 14535 | 2.3131          |
-| 0.3053        | 10.0  | 16150 | 2.4105          |
 ### 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: 1.8997
 ## Model description
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
+- 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
 ### Training results
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.8344        | 1.0   | 808  | 2.0296          |
+| 1.6264        | 2.0   | 1616 | 1.5976          |
+| 1.3414        | 3.0   | 2424 | 1.5269          |
+| 1.0791        | 4.0   | 3232 | 1.5254          |
+| 0.889         | 5.0   | 4040 | 1.5648          |
+| 0.7635        | 6.0   | 4848 | 1.5888          |
+| 0.6572        | 7.0   | 5656 | 1.7361          |
+| 0.5869        | 8.0   | 6464 | 1.7462          |
+| 0.4992        | 9.0   | 7272 | 1.8707          |
+| 0.4577        | 10.0  | 8080 | 1.8997          |
 ### Framework versions