End of training

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2597
-- Bleu: 0.03
-- Gen Len: 17.8329
+- Loss: 0.2581
+- Bleu: 0.0425
+- Gen Len: 17.7806
 
 ## Model description
 
@@ -39,9 +39,11 @@ 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: 6
+- eval_batch_size: 6
 - seed: 42
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 18
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 1
@@ -49,9 +51,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Bleu | Gen Len |
-|:-------------:|:-----:|:-----:|:---------------:|:----:|:-------:|
-| 0.2379        | 1.0   | 58095 | 0.2597          | 0.03 | 17.8329 |
+| Training Loss | Epoch | Step  | Validation Loss | Bleu   | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
+| 0.2411        | 1.0   | 51639 | 0.2581          | 0.0425 | 17.7806 |
 
 
 ### Framework versions