Update README.md
Browse files
README.md
CHANGED
|
@@ -33,6 +33,9 @@ More information needed
|
|
| 33 |
|
| 34 |
## Training procedure
|
| 35 |
|
|
|
|
|
|
|
|
|
|
| 36 |
### Training hyperparameters
|
| 37 |
|
| 38 |
The following hyperparameters were used during training:
|
|
|
|
| 33 |
|
| 34 |
## Training procedure
|
| 35 |
|
| 36 |
+
This model was trained with the same methodology as [https://huggingface.co/andresnowak/MNLP_M2_mcqa_model](MNLP_M2_mcqa_model), where we only do a feedforward on the prompt
|
| 37 |
+
we get the last logit token and we do cross entropy loss on that token and the 4 options of the question (so the idea is that we want to maximize the likelihood of the model
|
| 38 |
+
of printing the correct letter to the question)
|
| 39 |
### Training hyperparameters
|
| 40 |
|
| 41 |
The following hyperparameters were used during training:
|