update model card README.md

README.md

@@ -2,6 +2,8 @@
 license: mit
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: gpt2-summarization_reward_model
   results: []
@@ -13,6 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 # gpt2-summarization_reward_model
 
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7473
+- Accuracy: 0.6006
 
 ## Model description
 
@@ -32,26 +37,31 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
 - distributed_type: multi-GPU
-- gradient_accumulation_steps: 4
+- num_devices: 16
 - total_train_batch_size: 64
+- total_eval_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 0.01
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.01  | 15   | -1.1809         | 0.71     |
+| 0.6421        | 1.0   | 1451 | 0.6815          | 0.6036   |
+| 0.5893        | 2.0   | 2902 | 0.6764          | 0.6048   |
+| 0.5488        | 3.0   | 4353 | 0.7074          | 0.6012   |
+| 0.5187        | 4.0   | 5804 | 0.7254          | 0.6009   |
+| 0.5034        | 5.0   | 7255 | 0.7473          | 0.6006   |
 
 
 ### Framework versions
 
-- Transformers 4.25.1
+- Transformers 4.26.0
 - Pytorch 1.13.1+cu117
 - Datasets 2.8.0
 - Tokenizers 0.13.2