Model save

README.md

@@ -3,8 +3,6 @@ license: mit
 base_model: unicamp-dl/ptt5-small-t5-vocab
 tags:
 - generated_from_trainer
-datasets:
-- tiagoblima/qg_squad_v1_pt
 model-index:
 - name: t5_small-qg-aap
   results: []
@@ -15,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # t5_small-qg-aap
 
-This model is a fine-tuned version of [unicamp-dl/ptt5-small-t5-vocab](https://huggingface.co/unicamp-dl/ptt5-small-t5-vocab) on the tiagoblima/qg_squad_v1_pt dataset.
+This model is a fine-tuned version of [unicamp-dl/ptt5-small-t5-vocab](https://huggingface.co/unicamp-dl/ptt5-small-t5-vocab) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4213
+- Loss: 6.5105
 
 ## Model description
 
@@ -36,16 +34,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 0.005
 - train_batch_size: 64
-- eval_batch_size: 8
+- eval_batch_size: 4
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 15.0
+- num_epochs: 5.0
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 6.4555        | 1.0   | 808  | 8.1815          |
+| 5.7684        | 2.0   | 1616 | 7.3459          |
+| 5.3707        | 3.0   | 2424 | 6.8522          |
+| 5.1609        | 4.0   | 3232 | 6.5931          |
+| 5.1034        | 5.0   | 4040 | 6.5105          |
 
 
 ### Framework versions