update model card README.md

README.md

@@ -12,9 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # masked-sentence-generation
 
-This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
+This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.8396
+- Loss: nan
 
 ## Model description
 
@@ -34,40 +34,23 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 1
+- eval_batch_size: 1
 - seed: 42
 - gradient_accumulation_steps: 16
-- total_train_batch_size: 64
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 7
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 3.1508        | 0.32  | 100  | 2.8654          |
-| 3.0787        | 0.64  | 200  | 2.8532          |
-| 3.0573        | 0.96  | 300  | 2.8440          |
-| 2.984         | 1.28  | 400  | 2.8398          |
-| 2.9727        | 1.6   | 500  | 2.8364          |
-| 2.9781        | 1.92  | 600  | 2.8336          |
-| 2.9238        | 2.24  | 700  | 2.8346          |
-| 2.8974        | 2.56  | 800  | 2.8334          |
-| 2.894         | 2.88  | 900  | 2.8312          |
-| 2.8716        | 3.2   | 1000 | 2.8348          |
-| 2.8447        | 3.52  | 1100 | 2.8332          |
-| 2.8467        | 3.84  | 1200 | 2.8332          |
-| 2.8128        | 4.16  | 1300 | 2.8357          |
-| 2.8007        | 4.48  | 1400 | 2.8362          |
-| 2.8071        | 4.8   | 1500 | 2.8367          |
-| 2.796         | 5.12  | 1600 | 2.8380          |
-| 2.7628        | 5.44  | 1700 | 2.8387          |
-| 2.7694        | 5.76  | 1800 | 2.8378          |
-| 2.7734        | 6.08  | 1900 | 2.8384          |
-| 2.7473        | 6.4   | 2000 | 2.8403          |
-| 2.758         | 6.72  | 2100 | 2.8396          |
+| Training Loss                   | Epoch | Step | Validation Loss |
+|:-------------------------------:|:-----:|:----:|:---------------:|
+| 84911378280078883749363712.0000 | 1.5   | 100  | nan             |
+| 0.0                             | 2.99  | 200  | nan             |
+| 0.0                             | 4.49  | 300  | nan             |
+| 0.0                             | 5.98  | 400  | nan             |
 
 
 ### Framework versions