End of training

README.md

@@ -17,12 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [flax-community/spanish-t5-small](https://huggingface.co/flax-community/spanish-t5-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7310
-- Rouge1: 37.4282
-- Rouge2: 22.3689
-- Rougel: 36.6759
-- Rougelsum: 36.6221
-- Gen Len: 8.2137
+- Loss: 1.3716
+- Rouge1: 44.6732
+- Rouge2: 29.5427
+- Rougel: 44.3407
+- Rougelsum: 44.3626
+- Gen Len: 8.2906
 
 ## Model description
 
@@ -42,20 +42,21 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
-| 2.6393        | 1.0   | 264  | 1.9960          | 32.7681 | 17.2065 | 31.9063 | 31.833    | 8.3718  |
-| 1.9631        | 2.0   | 528  | 1.7823          | 38.1058 | 22.883  | 37.2227 | 37.1823   | 8.0598  |
-| 1.7671        | 3.0   | 792  | 1.7310          | 37.4282 | 22.3689 | 36.6759 | 36.6221   | 8.2137  |
+| 2.1475        | 1.0   | 527  | 1.7342          | 37.3065 | 21.7821 | 36.9349 | 36.853    | 8.2799  |
+| 1.6495        | 2.0   | 1054 | 1.5130          | 42.3167 | 26.6311 | 41.9494 | 41.8617   | 8.1496  |
+| 1.445         | 3.0   | 1581 | 1.4049          | 43.5614 | 28.5147 | 43.2416 | 43.2528   | 8.2585  |
+| 1.2756        | 4.0   | 2108 | 1.3716          | 44.6732 | 29.5427 | 44.3407 | 44.3626   | 8.2906  |
 
 
 ### Framework versions