update model card README.md

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Salesforce/codegen-350M-multi](https://huggingface.co/Salesforce/codegen-350M-multi) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0518
+- Loss: 0.0266
 
 ## Model description
 
@@ -34,10 +34,10 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 1
+- eval_batch_size: 1
 - seed: 42
-- gradient_accumulation_steps: 8
+- gradient_accumulation_steps: 32
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -47,9 +47,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 0.99  | 68   | 0.0652          |
-| No log        | 1.99  | 137  | 0.0545          |
-| No log        | 2.97  | 204  | 0.0518          |
+| No log        | 0.99  | 85   | 0.0406          |
+| No log        | 1.99  | 170  | 0.0297          |
+| No log        | 2.98  | 255  | 0.0266          |
 
 
 ### Framework versions