ujkim98
/

mt5-small-finetuned-amazon-en-es

text2text-generation

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

ujkim98 commited on Apr 23, 2023

Commit

4905c25

•

1 Parent(s): dcb939d

update model card README.md

Files changed (1) hide show

README.md +12 -12

README.md CHANGED Viewed

@@ -18,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.7922
-- Rouge1: 19.1653
-- Rouge2: 7.0586
-- Rougel: 17.6487
-- Rougelsum: 17.9202
 ## Model description
@@ -52,14 +52,14 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|
-| 11.9457       | 1.0   | 151  | 4.4346          | 6.0042  | 1.1556 | 5.9068  | 5.8435    |
-| 5.4958        | 2.0   | 302  | 3.4869          | 7.2729  | 1.8895 | 7.307   | 7.1446    |
-| 4.4559        | 3.0   | 453  | 3.1252          | 8.665   | 1.6278 | 8.4274  | 8.3353    |
-| 4.0657        | 4.0   | 604  | 2.9205          | 10.9136 | 3.4009 | 10.3961 | 10.4091   |
-| 3.828         | 5.0   | 755  | 2.8419          | 18.5917 | 6.8523 | 16.9087 | 17.2145   |
-| 3.6794        | 6.0   | 906  | 2.8178          | 18.9371 | 7.0542 | 17.1941 | 17.4368   |
-| 3.6205        | 7.0   | 1057 | 2.7984          | 19.0788 | 7.0287 | 17.4496 | 17.8402   |
-| 3.5711        | 8.0   | 1208 | 2.7922          | 19.1653 | 7.0586 | 17.6487 | 17.9202   |
 ### Framework versions

 This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.7922
+- Rouge1: 18.97
+- Rouge2: 7.0348
+- Rougel: 17.6971
+- Rougelsum: 17.882
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|
+| 11.9457       | 1.0   | 151  | 4.4346          | 5.986   | 1.1429 | 5.9458  | 5.7994    |
+| 5.4958        | 2.0   | 302  | 3.4869          | 7.1658  | 1.8822 | 7.2823  | 7.1334    |
+| 4.4559        | 3.0   | 453  | 3.1252          | 8.5582  | 1.605  | 8.3697  | 8.302     |
+| 4.0657        | 4.0   | 604  | 2.9205          | 10.6565 | 3.4667 | 10.4793 | 10.3928   |
+| 3.828         | 5.0   | 755  | 2.8419          | 18.3545 | 6.8241 | 17.013  | 17.3331   |
+| 3.6794        | 6.0   | 906  | 2.8178          | 18.6777 | 7.0318 | 17.2025 | 17.3807   |
+| 3.6205        | 7.0   | 1057 | 2.7984          | 18.8984 | 7.0004 | 17.4826 | 17.7813   |
+| 3.5711        | 8.0   | 1208 | 2.7922          | 18.97   | 7.0348 | 17.6971 | 17.882    |
 ### Framework versions