Modelo entrenado con reseñas de Amazon

README.md

@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.2475
-- Bleu: 3.9802
-- Gen Len: 8.7247
+- Loss: 2.6291
+- Bleu: 2.7651
+- Gen Len: 9.814
 
 ## Model description
 
@@ -46,18 +46,14 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 6
+- num_epochs: 2
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Bleu   | Gen Len |
-|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
-| 2.6379        | 1.0   | 1875  | 2.3908          | 3.9477 | 9.194   |
-| 2.3936        | 2.0   | 3750  | 2.3024          | 4.468  | 8.904   |
-| 2.3899        | 3.0   | 5625  | 2.2838          | 4.0933 | 8.526   |
-| 2.2805        | 4.0   | 7500  | 2.2567          | 3.8025 | 8.6367  |
-| 2.2141        | 5.0   | 9375  | 2.2480          | 3.8739 | 8.7533  |
-| 2.2243        | 6.0   | 11250 | 2.2475          | 3.9802 | 8.7247  |
+| Training Loss | Epoch | Step | Validation Loss | Bleu   | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
+| 3.0026        | 1.0   | 625  | 2.6722          | 3.5767 | 9.624   |
+| 2.7396        | 2.0   | 1250 | 2.6291          | 2.7651 | 9.814   |
 
 
 ### Framework versions