Update README.md
Browse files
README.md
CHANGED
@@ -46,9 +46,7 @@ We use the pretrained [`sentence-transformers/all-mpnet-base-v2`](https://huggin
|
|
46 |
However, we reduce the processed sequence length to 384 to reduce the training time of the model.
|
47 |
Regarding other hyperparameters, we use the same interaction data batch size of 1024; we use the negative sampling parameter m = 10000.
|
48 |
We use constant learning rate of 1e-5, and we train the model for ten epochs.
|
49 |
-
For deatils please see our paper (link TBA).
|
50 |
-
|
51 |
-
We finetuned our model on both Goodbooks-10k and MovieLens-20M datasets.
|
52 |
For item ids used during training please see (links TBA).
|
53 |
|
54 |
## Evaluation Results
|
|
|
46 |
However, we reduce the processed sequence length to 384 to reduce the training time of the model.
|
47 |
Regarding other hyperparameters, we use the same interaction data batch size of 1024; we use the negative sampling parameter m = 10000.
|
48 |
We use constant learning rate of 1e-5, and we train the model for ten epochs.
|
49 |
+
We finetuned our model on both Goodbooks-10k and MovieLens-20M datasets. For deatils please see our paper (link TBA).
|
|
|
|
|
50 |
For item ids used during training please see (links TBA).
|
51 |
|
52 |
## Evaluation Results
|