ingridnc
/

t5-small-finetuned-fi-to-en

Text2Text Generation Transformers PyTorch TensorBoard

t5 generated_from_trainer Eval Results Inference Endpoints text-generation-inference

Model card Files Files and versions Metrics Training metrics Community

ingridnc commited on Dec 6, 2021

Commit

bc78fc4

•

1 Parent(s): 2f24652

update model card README.md

Files changed (1) hide show

README.md +10 -7

README.md CHANGED Viewed

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: Bleu
       type: bleu
-      value: 1.4028
 ---
 <!-- 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 wmt19 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.4526
-- Bleu: 1.4028
-- Gen Len: 17.2763
 ## Model description
@@ -56,15 +56,18 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
 - mixed_precision_training: Native AMP
 ### Training results
 | Training Loss | Epoch | Step  | Validation Loss | Bleu   | Gen Len |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
-| 3.2947        | 1.0   | 6250  | 3.4835          | 1.3506 | 17.2077 |
-| 3.2321        | 2.0   | 12500 | 3.4526          | 1.4028 | 17.2763 |
 ### Framework versions

     metrics:
     - name: Bleu
       type: bleu
+      value: 1.618
 ---
 <!-- 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 wmt19 dataset.
 It achieves the following results on the evaluation set:
+- Loss: 3.3598
+- Bleu: 1.618
+- Gen Len: 17.3223
 ## Model description
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 ### Training results
 | Training Loss | Epoch | Step  | Validation Loss | Bleu   | Gen Len |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
+| 3.3627        | 1.0   | 6250  | 3.5122          | 1.2882 | 17.1803 |
+| 3.2162        | 2.0   | 12500 | 3.4442          | 1.4329 | 17.2617 |
+| 3.1304        | 3.0   | 18750 | 3.3872          | 1.4862 | 17.296  |
+| 3.0832        | 4.0   | 25000 | 3.3648          | 1.5795 | 17.3047 |
+| 3.0623        | 5.0   | 31250 | 3.3598          | 1.618  | 17.3223 |
 ### Framework versions