clagp16
/

mt5-neutralization

text2text-generation

Generated from Trainer

Model card Files Files and versions

clagp16 commited on 19 days ago

Commit

c050471

·

verified ·

1 Parent(s): 4c5da7d

Training complete

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -19,9 +19,9 @@ 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: 0.2728
-- Bleu: 78.8761
-- Gen Len: 17.1562
 ## Model description
@@ -52,8 +52,8 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| No log        | 1.0   | 440  | 0.3447          | 75.522  | 16.5833 |
-| 0.8685        | 2.0   | 880  | 0.2728          | 78.8761 | 17.1562 |
 ### 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: 0.5274
+- Bleu: 34.1293
+- Gen Len: 13.0625
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
+| No log        | 1.0   | 440  | 0.7114          | 35.1066 | 13.7604 |
+| 5.5015        | 2.0   | 880  | 0.5274          | 34.1293 | 13.0625 |
 ### Framework versions