update model card README.md

README.md

@@ -12,9 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # HintsGenerator
 
-This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
+This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1726
+- Loss: 1.7536
 
 ## Model description
 
@@ -34,7 +34,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 128
+- train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -43,15 +43,15 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 3.3501        | 1.0   | 527  | 2.3548          |
-| 2.6694        | 2.0   | 1054 | 2.2615          |
-| 2.5871        | 3.0   | 1581 | 2.2202          |
-| 2.5442        | 4.0   | 2108 | 2.1957          |
-| 2.5154        | 5.0   | 2635 | 2.1837          |
-| 2.4983        | 6.0   | 3162 | 2.1757          |
-| 2.4929        | 7.0   | 3689 | 2.1726          |
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 2.1364        | 1.0   | 2106  | 1.8266          |
+| 2.0131        | 2.0   | 4212  | 1.7688          |
+| 1.9435        | 3.0   | 6318  | 1.7572          |
+| 1.8904        | 4.0   | 8424  | 1.7694          |
+| 1.8695        | 5.0   | 10530 | 1.7581          |
+| 1.8502        | 6.0   | 12636 | 1.7571          |
+| 1.8284        | 7.0   | 14742 | 1.7536          |
 
 
 ### Framework versions