Update README.md

README.md

@@ -87,10 +87,37 @@ Use the code below to get started with the model.
 
 [More Information Needed]
 
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-4
+- per_device_train_batch_size=4
+- eval_batch_size: 2
+- evaluation_strategy="steps"
+- gradient_checkpointing=True
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- num_train_epochs=3
+- save_total_limit=1
+- fp16=True
+- save_steps=400
+- eval_steps=200
+- logging_steps=200
+- push_to_hub=True
+
+### Training results
+
+| Training Loss | WER   | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 6.427         | 0.33  | 200   | 0.5634          |
+| 0.5994        | 0.67  | 400   | 0.5290          |
+| 0.584         | 1.0   | 600   | 0.4924          |
+| 0.5589        | 1.33  | 800   | 0.4828          |
+| 0.5747        | 1.67  | 1000  | 0.4848          |
+| 0.5904        | 2.0   | 1200  | 0.4831          |
+|
 
-#### Training Hyperparameters
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
 
 #### Speeds, Sizes, Times [optional]