marciovbarbosa
/

t5-small-finetuned-de-to-en-lr1e-4

Text2Text Generation

generated_from_trainer

Inference Endpoints

text-generation-inference

Model card Files Files and versions Metrics Training metrics Community

marciovbarbosa commited on Dec 4, 2021

Commit

a25a8c3

•

1 Parent(s): 0f215ae

update model card README.md

Files changed (1) hide show

README.md +14 -14

README.md CHANGED Viewed

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: Bleu
       type: bleu
-      value: 11.3891
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,9 +29,9 @@ 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 the wmt16 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8982
-- Bleu: 11.3891
-- Gen Len: 17.2881
 ## Model description
@@ -62,16 +62,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| No log        | 1.0   | 272  | 2.0257          | 9.1145  | 17.3171 |
-| 2.4581        | 2.0   | 544  | 1.9562          | 10.3226 | 17.3218 |
-| 2.4581        | 3.0   | 816  | 1.9339          | 10.5298 | 17.3414 |
-| 2.1446        | 4.0   | 1088 | 1.9203          | 10.8193 | 17.3398 |
-| 2.1446        | 5.0   | 1360 | 1.9070          | 10.9929 | 17.2848 |
-| 1.9797        | 6.0   | 1632 | 1.9036          | 11.2258 | 17.3258 |
-| 1.9797        | 7.0   | 1904 | 1.8966          | 11.3839 | 17.3044 |
-| 1.8939        | 8.0   | 2176 | 1.8999          | 11.4197 | 17.2768 |
-| 1.8939        | 9.0   | 2448 | 1.8971          | 11.4326 | 17.2791 |
-| 1.8365        | 10.0  | 2720 | 1.8982          | 11.3891 | 17.2881 |
 ### Framework versions

     metrics:
     - name: Bleu
       type: bleu
+      value: 11.427
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the wmt16 dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.8228
+- Bleu: 11.427
+- Gen Len: 17.2674
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
+| No log        | 1.0   | 272  | 1.9605          | 9.0786  | 17.3148 |
+| 2.3992        | 2.0   | 544  | 1.8884          | 10.1443 | 17.3301 |
+| 2.3992        | 3.0   | 816  | 1.8647          | 10.4816 | 17.3258 |
+| 2.0832        | 4.0   | 1088 | 1.8473          | 10.7396 | 17.3231 |
+| 2.0832        | 5.0   | 1360 | 1.8343          | 11.0937 | 17.2621 |
+| 1.9193        | 6.0   | 1632 | 1.8282          | 11.1303 | 17.3098 |
+| 1.9193        | 7.0   | 1904 | 1.8234          | 11.2971 | 17.2991 |
+| 1.8351        | 8.0   | 2176 | 1.8241          | 11.3433 | 17.2621 |
+| 1.8351        | 9.0   | 2448 | 1.8224          | 11.394  | 17.2691 |
+| 1.7747        | 10.0  | 2720 | 1.8228          | 11.427  | 17.2674 |
 ### Framework versions