chakochen
/

mt5-destination-inference

text2text-generation

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

chakochen commited on Sep 27, 2023

Commit

0b5a1fa

•

1 Parent(s): 9f4c632

Training complete

Files changed (1) hide show

README.md +12 -12

README.md CHANGED Viewed

@@ -18,11 +18,11 @@ 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 the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 5.5749
-- Rouge1: 0.1757
 - Rouge2: 0.0
-- Rougel: 0.1757
-- Rougelsum: 0.1757
 ## Model description
@@ -53,14 +53,14 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
-| 20.4559       | 1.0   | 250  | 8.6810          | 0.0    | 0.0    | 0.0    | 0.0       |
-| 9.5672        | 2.0   | 500  | 5.4642          | 0.0    | 0.0    | 0.0    | 0.0       |
-| 6.3205        | 3.0   | 750  | 5.6638          | 0.0    | 0.0    | 0.0    | 0.0       |
-| 5.3432        | 4.0   | 1000 | 5.6325          | 0.1757 | 0.0    | 0.1757 | 0.1757    |
-| 4.9042        | 5.0   | 1250 | 5.6978          | 0.0    | 0.0    | 0.0    | 0.0       |
-| 4.6882        | 6.0   | 1500 | 5.6566          | 0.0    | 0.0    | 0.0    | 0.0       |
-| 4.538         | 7.0   | 1750 | 5.5962          | 0.0    | 0.0    | 0.0    | 0.0       |
-| 4.4857        | 8.0   | 2000 | 5.5749          | 0.1757 | 0.0    | 0.1757 | 0.1757    |
 ### Framework versions

 This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 3.0350
+- Rouge1: 4.0
 - Rouge2: 0.0
+- Rougel: 4.0
+- Rougelsum: 4.0
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
+| 20.4559       | 1.0   | 250  | 9.7574          | 0.0    | 0.0    | 0.0    | 0.0       |
+| 9.5672        | 2.0   | 500  | 4.8087          | 0.0    | 0.0    | 0.0    | 0.0       |
+| 6.3205        | 3.0   | 750  | 3.9127          | 0.2    | 0.0    | 0.2    | 0.2       |
+| 5.3432        | 4.0   | 1000 | 3.5081          | 1.4    | 0.0    | 1.4    | 1.4       |
+| 4.9042        | 5.0   | 1250 | 3.3167          | 2.2    | 0.0    | 2.2    | 2.2       |
+| 4.6882        | 6.0   | 1500 | 3.1341          | 3.2    | 0.0    | 3.2    | 3.2       |
+| 4.538         | 7.0   | 1750 | 3.0736          | 4.0    | 0.0    | 4.0    | 4.0       |
+| 4.4857        | 8.0   | 2000 | 3.0350          | 4.0    | 0.0    | 4.0    | 4.0       |
 ### Framework versions