update model card README.md

README.md

@@ -2,8 +2,6 @@
 license: apache-2.0
 tags:
 - generated_from_trainer
-datasets:
-- cosmos_qa
 metrics:
 - accuracy
 model-index:
@@ -16,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # t5_small_race_mutlirc
 
-This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the cosmos_qa dataset.
+This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5929
-- Accuracy: 0.4794
+- Loss: 0.5760
+- Accuracy: 0.5259
 
 ## Model description
 
@@ -38,22 +36,22 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 0.0001
 - train_batch_size: 8
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 50
+- lr_scheduler_warmup_steps: 1000
 - num_epochs: 3.0
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.7069        | 1.0   | 1250 | 0.6522          | 0.396    |
-| 0.6595        | 2.0   | 2500 | 0.6009          | 0.4693   |
-| 0.6374        | 3.0   | 3750 | 0.5929          | 0.4794   |
+| Training Loss | Epoch | Step  | Accuracy | Validation Loss |
+|:-------------:|:-----:|:-----:|:--------:|:---------------:|
+| 0.6043        | 1.0   | 14141 | 0.4832   | 0.5925          |
+| 0.5647        | 2.0   | 28282 | 0.5152   | 0.5659          |
+| 0.5237        | 3.0   | 42423 | 0.5760   | 0.5259          |
 
 
 ### Framework versions