Miranda
/

t5-small-train

text2text-generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions Metrics Training metrics Community

Miranda commited on Apr 30, 2022

Commit

ae517bc

·

1 Parent(s): ae75e97

update model card README.md

Files changed (1) hide show

README.md +13 -13

README.md CHANGED Viewed

@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.3177
-- Rouge1: 42.593
-- Rouge2: 20.4119
-- Rougel: 37.9869
-- Rougelsum: 38.7572
 ## Model description
@@ -52,14 +52,14 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
-| 2.11          | 1.0   | 40   | 2.3312          | 41.6952 | 20.5706 | 37.2314 | 38.0437   |
-| 2.0322        | 2.0   | 80   | 2.3218          | 42.0754 | 20.614  | 37.4971 | 38.3932   |
-| 1.9806        | 3.0   | 120  | 2.3205          | 42.257  | 20.6839 | 37.7397 | 38.4623   |
-| 1.9656        | 4.0   | 160  | 2.3229          | 42.2486 | 20.0638 | 37.5846 | 38.4475   |
-| 1.9416        | 5.0   | 200  | 2.3208          | 42.764  | 20.588  | 38.0969 | 38.9356   |
-| 1.9139        | 6.0   | 240  | 2.3187          | 42.6413 | 20.7776 | 38.0375 | 38.8627   |
-| 1.8388        | 7.0   | 280  | 2.3181          | 43.0338 | 21.0632 | 38.3891 | 39.1829   |
-| 1.9099        | 8.0   | 320  | 2.3177          | 42.593  | 20.4119 | 37.9869 | 38.7572   |
 ### Framework versions

 This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 2.2904
+- Rouge1: 43.1094
+- Rouge2: 21.2923
+- Rougel: 38.135
+- Rougelsum: 38.5859
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
+| 3.3148        | 1.0   | 40   | 2.7417          | 34.0264 | 14.7557 | 28.7117 | 29.5721   |
+| 2.7401        | 2.0   | 80   | 2.4961          | 39.0024 | 18.7472 | 34.303  | 34.664    |
+| 2.5794        | 3.0   | 120  | 2.3920          | 41.0853 | 19.9154 | 36.3782 | 36.8037   |
+| 2.4811        | 4.0   | 160  | 2.3454          | 41.775  | 19.5823 | 36.7877 | 37.133    |
+| 2.3678        | 5.0   | 200  | 2.3171          | 42.2607 | 20.6337 | 37.6722 | 38.031    |
+| 2.3998        | 6.0   | 240  | 2.3014          | 43.7874 | 21.5906 | 38.6818 | 39.1065   |
+| 2.2967        | 7.0   | 280  | 2.2926          | 43.2068 | 21.3236 | 38.1984 | 38.6565   |
+| 2.2779        | 8.0   | 320  | 2.2904          | 43.1094 | 21.2923 | 38.135  | 38.5859   |
 ### Framework versions