psxjp5
/

mlm_old

Text Generation

Generated from Trainer

Inference Endpoints

text-generation-inference

Model card Files Files and versions Metrics Training metrics Community

psxjp5 commited on Aug 2, 2023

Commit

c300fde

•

1 Parent(s): 61afd85

Update README.md

Files changed (1) hide show

README.md +9 -9

README.md CHANGED Viewed

@@ -46,15 +46,15 @@ The following hyperparameters were used during training:
 ### Training results
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 12.948        | 0.99  | 22   | 5.1466          |
-| 4.061         | 1.98  | 44   | 4.3114          |
-| 3.7125        | 2.97  | 66   | 4.0807          |
-| 3.6033        | 3.96  | 88   | 4.0553          |
-| 3.5032        | 4.94  | 110  | 4.0514          |
-| 3.4427        | 5.93  | 132  | 4.0879          |
-| 3.3968        | 6.92  | 154  | 4.0711          |
 ### Framework versions

 ### Training results
+| Training Loss | Epoch | Step | Validation Loss | Perplexity |
+|:-------------:|:-----:|:----:|:---------------:|:----------:|
+| 12.948        | 0.99  | 22   | 5.1466          | 171.85     |
+| 4.061         | 1.98  | 44   | 4.3114          | 74.54      |
+| 3.7125        | 2.97  | 66   | 4.0807          | 59.19      |
+| 3.6033        | 3.96  | 88   | 4.0553          | 57.70      |
+| 3.5032        | 4.94  | 110  | 4.0514          | 57.48      |
+| 3.4427        | 5.93  | 132  | 4.0879          | 59.61      |
+| 3.3968        | 6.92  | 154  | 4.0711          | 58.62      |
 ### Framework versions