jojoUla
/

bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-40

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

jojoUla commited on Feb 27, 2023

Commit

6b064a0

•

1 Parent(s): 72817a1

update model card README.md

Files changed (1) hide show

README.md +22 -12

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 [jojoUla/bert-large-cased-sigir-support-refute-no-label-40](https://huggingface.co/jojoUla/bert-large-cased-sigir-support-refute-no-label-40) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.8726
 ## Model description
@@ -39,23 +39,33 @@ 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: 10.0
 - mixed_precision_training: Native AMP
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.3922        | 1.0   | 1    | 7.7770          |
-| 5.775         | 2.0   | 2    | 7.9736          |
-| 7.0239        | 3.0   | 3    | 5.2036          |
-| 4.0829        | 4.0   | 4    | 2.9272          |
-| 3.4724        | 5.0   | 5    | 5.9639          |
-| 2.5963        | 6.0   | 6    | 3.5008          |
-| 3.4139        | 7.0   | 7    | 2.1127          |
-| 2.5872        | 8.0   | 8    | 3.6687          |
-| 2.9188        | 9.0   | 9    | 3.8722          |
-| 1.62          | 10.0  | 10   | 2.6152          |
 ### Framework versions

 This model is a fine-tuned version of [jojoUla/bert-large-cased-sigir-support-refute-no-label-40](https://huggingface.co/jojoUla/bert-large-cased-sigir-support-refute-no-label-40) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 2.0129
 ## Model description
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 20.0
 - mixed_precision_training: Native AMP
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 6.5696        | 1.0   | 1    | 9.6780          |
+| 6.1387        | 2.0   | 2    | 7.6930          |
+| 6.0476        | 3.0   | 3    | 2.0548          |
+| 4.641         | 4.0   | 4    | 2.4165          |
+| 3.1222        | 5.0   | 5    | 1.3710          |
+| 3.1408        | 6.0   | 6    | 0.0085          |
+| 3.8796        | 7.0   | 7    | 1.6208          |
+| 2.1958        | 8.0   | 8    | 2.1868          |
+| 1.784         | 9.0   | 9    | 3.6380          |
+| 1.1978        | 10.0  | 10   | 2.4740          |
+| 1.1285        | 11.0  | 11   | 1.9132          |
+| 1.5405        | 12.0  | 12   | 2.8283          |
+| 2.3517        | 13.0  | 13   | 2.8707          |
+| 1.4499        | 14.0  | 14   | 2.6103          |
+| 1.3109        | 15.0  | 15   | 1.3650          |
+| 0.6503        | 16.0  | 16   | 1.5220          |
+| 1.3603        | 17.0  | 17   | 2.9103          |
+| 1.2949        | 18.0  | 18   | 3.7889          |
+| 0.9998        | 19.0  | 19   | 1.3546          |
+| 0.7517        | 20.0  | 20   | 1.3265          |
 ### Framework versions