End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [DeepESP/gpt2-spanish](https://huggingface.co/DeepESP/gpt2-spanish) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.5965
+- Loss: 2.5287
 
 ## Model description
 
@@ -34,24 +34,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1.5e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 2.5e-05
+- 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: 6
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.8648        | 1.0   | 20   | 2.7875          |
-| 2.6771        | 2.0   | 40   | 2.6787          |
-| 2.5709        | 3.0   | 60   | 2.6329          |
-| 2.518         | 4.0   | 80   | 2.6113          |
-| 2.4107        | 5.0   | 100  | 2.5996          |
-| 2.4662        | 6.0   | 120  | 2.5965          |
+| 2.8091        | 1.0   | 40   | 2.6299          |
+| 2.3812        | 2.0   | 80   | 2.5587          |
+| 2.2525        | 3.0   | 120  | 2.5377          |
+| 2.1789        | 4.0   | 160  | 2.5308          |
+| 2.1258        | 5.0   | 200  | 2.5287          |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:126e4afda6f52c571a77d5fed52265f0af89fff38dd359654cfb5eded9e3be47
+oid sha256:de3ed75972c1b83582cca78a41b1b5c6412f6536da7097726dde53d38479b5d2
 size 497807197

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0040ba09f06d5f778974eb3b3b5273e96d26fb7193c13ba7dc4bb17833f55a6
+oid sha256:7317fae08b9be26bc6a609041b83209a0eb4b7a04684ca15fb19a6b0671a9028
 size 4027