Updating model weights

README.md

@@ -98,9 +98,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.9069, 0.4847],
-#         [0.9069, 1.0000, 0.4705],
-#         [0.4847, 0.4705, 1.0000]])
+# tensor([[1.0000, 0.9040, 0.4661],
+#         [0.9040, 1.0000, 0.4580],
+#         [0.4661, 0.4580, 1.0000]])
 ```
 
 <!--
@@ -170,7 +170,7 @@ You can finetune this model on your own dataset.
 ### Training Hyperparameters
 #### Non-Default Hyperparameters
 
-- `per_device_train_batch_size`: 16
+- `per_device_train_batch_size`: 32
 - `per_device_eval_batch_size`: 16
 - `learning_rate`: 2e-05
 - `weight_decay`: 0.001
@@ -192,7 +192,7 @@ You can finetune this model on your own dataset.
 - `do_predict`: False
 - `eval_strategy`: no
 - `prediction_loss_only`: True
-- `per_device_train_batch_size`: 16
+- `per_device_train_batch_size`: 32
 - `per_device_eval_batch_size`: 16
 - `per_gpu_train_batch_size`: None
 - `per_gpu_eval_batch_size`: None
@@ -311,9 +311,9 @@ You can finetune this model on your own dataset.
 ### Training Logs
 | Epoch  | Step | Training Loss |
 |:------:|:----:|:-------------:|
-| 0.0233 | 1    | 2.5914        |
-| 1.0    | 43   | 2.1891        |
-| 2.0    | 86   | 1.7619        |
+| 0.0455 | 1    | 3.3947        |
+| 1.0    | 22   | 2.7364        |
+| 2.0    | 44   | 2.331         |
 
 
 ### Framework Versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bccec747373ecea8f1c3bdf519dde342408be7eea18dc3f52b4fb3378ddbc1df
+oid sha256:be3672f9b857e152eeff006caa019cc658f72b3fd342c173bbfbaefdfc2a8538
 size 90864192