jgammack
/

SAE-bert-base-uncased

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

jgammack commited on Feb 7, 2022

Commit

22d9b03

·

1 Parent(s): f000ce2

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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.6185
 ## Model description
@@ -46,21 +46,21 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.1189        | 1.0   | 80   | 2.7736          |
-| 2.9251        | 2.0   | 160  | 2.6334          |
-| 2.8013        | 3.0   | 240  | 2.6324          |
-| 2.7389        | 4.0   | 320  | 2.6143          |
-| 2.6959        | 5.0   | 400  | 2.6288          |
-| 2.6777        | 6.0   | 480  | 2.6220          |
-| 2.6519        | 7.0   | 560  | 2.5340          |
-| 2.6213        | 8.0   | 640  | 2.5730          |
-| 2.5859        | 9.0   | 720  | 2.5462          |
-| 2.5589        | 10.0  | 800  | 2.5119          |
-| 2.5551        | 11.0  | 880  | 2.5128          |
-| 2.5167        | 12.0  | 960  | 2.4869          |
-| 2.481         | 13.0  | 1040 | 2.5571          |
-| 2.5031        | 14.0  | 1120 | 2.5218          |
-| 2.5042        | 15.0  | 1200 | 2.4911          |
 ### Framework versions

 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 2.1256
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 2.5967        | 1.0   | 80   | 2.3409          |
+| 2.4881        | 2.0   | 160  | 2.2707          |
+| 2.3567        | 3.0   | 240  | 2.3134          |
+| 2.3413        | 4.0   | 320  | 2.2592          |
+| 2.3006        | 5.0   | 400  | 2.2351          |
+| 2.2568        | 6.0   | 480  | 2.2556          |
+| 2.2303        | 7.0   | 560  | 2.2546          |
+| 2.1892        | 8.0   | 640  | 2.1868          |
+| 2.1851        | 9.0   | 720  | 2.2073          |
+| 2.1738        | 10.0  | 800  | 2.1344          |
+| 2.1673        | 11.0  | 880  | 2.1927          |
+| 2.1518        | 12.0  | 960  | 2.1844          |
+| 2.1142        | 13.0  | 1040 | 2.1466          |
+| 2.1343        | 14.0  | 1120 | 2.2024          |
+| 2.1332        | 15.0  | 1200 | 2.1035          |
 ### Framework versions