Training in progress, epoch 1

final/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, 0.8937, 0.4770],
-#         [0.8937, 1.0000, 0.4732],
-#         [0.4770, 0.4732, 1.0000]])
+# tensor([[1.0000, 0.8965, 0.4641],
+#         [0.8965, 1.0000, 0.4616],
+#         [0.4641, 0.4616, 1.0000]])
 ```
 
 <!--
@@ -172,9 +172,9 @@ You can finetune this model on your own dataset.
 
 - `per_device_train_batch_size`: 32
 - `per_device_eval_batch_size`: 16
-- `learning_rate`: 1e-05
+- `learning_rate`: 2e-05
 - `weight_decay`: 0.001
-- `num_train_epochs`: 6
+- `num_train_epochs`: 2
 - `warmup_ratio`: 0.2
 - `fp16`: True
 - `dataloader_num_workers`: 2
@@ -199,13 +199,13 @@ You can finetune this model on your own dataset.
 - `gradient_accumulation_steps`: 1
 - `eval_accumulation_steps`: None
 - `torch_empty_cache_steps`: None
-- `learning_rate`: 1e-05
+- `learning_rate`: 2e-05
 - `weight_decay`: 0.001
 - `adam_beta1`: 0.9
 - `adam_beta2`: 0.999
 - `adam_epsilon`: 1e-08
 - `max_grad_norm`: 1.0
-- `num_train_epochs`: 6
+- `num_train_epochs`: 2
 - `max_steps`: -1
 - `lr_scheduler_type`: linear
 - `lr_scheduler_kwargs`: {}
@@ -312,12 +312,8 @@ You can finetune this model on your own dataset.
 | Epoch  | Step | Training Loss |
 |:------:|:----:|:-------------:|
 | 0.0455 | 1    | 3.3947        |
-| 1.0    | 22   | 2.9755        |
-| 2.0    | 44   | 2.8228        |
-| 3.0    | 66   | 2.6316        |
-| 4.0    | 88   | 2.4885        |
-| 5.0    | 110  | 2.4066        |
-| 6.0    | 132  | 2.4311        |
+| 1.0    | 22   | 2.8004        |
+| 2.0    | 44   | 2.4666        |
 
 
 ### Framework Versions

final/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f35e9fc17b1dead17057de429ab6bae16262ea5718de8465be0dc823cf9b7c78
+oid sha256:7f4e1bfa7de51fde73187ce4b32fd4bcc39e11be28236be9ab0b752a3df6dd48
 size 90864192

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f4e1bfa7de51fde73187ce4b32fd4bcc39e11be28236be9ab0b752a3df6dd48
+oid sha256:56aa0a763e86f0d86e91e4c4afcbf7fbae28a1d4c27cbbed96c0b10ec2118d07
 size 90864192

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92d5a20586e1e0b0b585e149a74b68da5abb96f10841c23444985b42d5be4961
+oid sha256:849402676e03b666436dfa0358e1b7772cd390876fa060da707913822f48ffe5
 size 5752