pszemraj
/

bart-base-instructiongen-w-inputs

Text2Text Generation

Inference Endpoints

Model card Files Files and versions Community

pszemraj commited on Apr 28, 2023

Commit

f270c7e

•

1 Parent(s): c9d3b43

Update README.md

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -65,11 +65,13 @@ inference:
   parameters:
     max_length: 96
     num_beams: 4
 datasets:
 - pszemraj/fleece2instructions-inputs-alpaca-cleaned
 language:
 - en
 pipeline_tag: text2text-generation
 ---
@@ -129,5 +131,4 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
 | 1.1147        | 1.0   | 680  | 0.9901          | 61.8451 | 38.8293 | 58.3372 | 59.8658   | 25.2401 |
-| 0.9565        | 2.0   | 1360 | 0.9579          | 62.3604 | 39.5109 | 58.8843 | 60.4494   | 24.9917 |

   parameters:
     max_length: 96
     num_beams: 4
+    early_stopping: true
 datasets:
 - pszemraj/fleece2instructions-inputs-alpaca-cleaned
 language:
 - en
 pipeline_tag: text2text-generation
+library_name: transformers
 ---
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
 | 1.1147        | 1.0   | 680  | 0.9901          | 61.8451 | 38.8293 | 58.3372 | 59.8658   | 25.2401 |
+| 0.9565        | 2.0   | 1360 | 0.9579          | 62.3604 | 39.5109 | 58.8843 | 60.4494   | 24.9917 |