64.5

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [avsolatorio/GIST-large-Embedding-v0](https://huggingface.co/avsolatorio/GIST-large-Embedding-v0) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1404
-- F1: 0.6842
+- Loss: 1.1814
+- F1: 0.6733
 
 ## Model description
 
@@ -37,39 +37,34 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3.887e-05
+- learning_rate: 6.445e-05
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 44
-- num_epochs: 20
+- lr_scheduler_warmup_steps: 35
+- num_epochs: 15
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.9899        | 1.0   | 199  | 0.8943          | 0.5434 |
-| 0.5878        | 2.0   | 398  | 0.8040          | 0.6147 |
-| 0.3657        | 3.0   | 597  | 0.8181          | 0.6132 |
-| 0.2319        | 4.0   | 796  | 0.7678          | 0.6420 |
-| 0.1497        | 5.0   | 995  | 0.8567          | 0.6385 |
-| 0.103         | 6.0   | 1194 | 0.8607          | 0.6603 |
-| 0.066         | 7.0   | 1393 | 0.8711          | 0.6414 |
-| 0.0464        | 8.0   | 1592 | 0.9418          | 0.6908 |
-| 0.0353        | 9.0   | 1791 | 0.9508          | 0.6815 |
-| 0.0274        | 10.0  | 1990 | 0.9942          | 0.6771 |
-| 0.0232        | 11.0  | 2189 | 1.0016          | 0.6846 |
-| 0.0201        | 12.0  | 2388 | 1.0156          | 0.6914 |
-| 0.018         | 13.0  | 2587 | 1.0488          | 0.6958 |
-| 0.0164        | 14.0  | 2786 | 1.0911          | 0.6808 |
-| 0.0153        | 15.0  | 2985 | 1.0688          | 0.6901 |
-| 0.0143        | 16.0  | 3184 | 1.1095          | 0.6798 |
-| 0.0135        | 17.0  | 3383 | 1.1022          | 0.6794 |
-| 0.0129        | 18.0  | 3582 | 1.1310          | 0.6812 |
-| 0.0124        | 19.0  | 3781 | 1.1359          | 0.6842 |
-| 0.0123        | 20.0  | 3980 | 1.1404          | 0.6842 |
+| 0.1774        | 1.0   | 199  | 0.8753          | 0.6349 |
+| 0.1386        | 2.0   | 398  | 0.9342          | 0.6269 |
+| 0.0978        | 3.0   | 597  | 0.8963          | 0.6481 |
+| 0.0557        | 4.0   | 796  | 1.0566          | 0.6269 |
+| 0.0378        | 5.0   | 995  | 0.8824          | 0.6875 |
+| 0.0207        | 6.0   | 1194 | 0.9721          | 0.6822 |
+| 0.0134        | 7.0   | 1393 | 1.0296          | 0.6728 |
+| 0.0103        | 8.0   | 1592 | 1.0678          | 0.6679 |
+| 0.0089        | 9.0   | 1791 | 1.1085          | 0.6722 |
+| 0.0079        | 10.0  | 1990 | 1.1080          | 0.6608 |
+| 0.0072        | 11.0  | 2189 | 1.1454          | 0.6718 |
+| 0.0066        | 12.0  | 2388 | 1.1474          | 0.6700 |
+| 0.0063        | 13.0  | 2587 | 1.1681          | 0.6694 |
+| 0.0061        | 14.0  | 2786 | 1.1827          | 0.6755 |
+| 0.006         | 15.0  | 2985 | 1.1814          | 0.6733 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19f55064024e9e3130a6882cd108e3c5001706e19e59af0ccf2907c3a5f4162d
+oid sha256:bf1dc159893323fdf78e29b618943a5b8e8d25d024959f1e59257e00ea97b09a
 size 1340688368

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5edbf0827c0741655db5edf96767bfc5e4e8b44b936a2776b3dd61ded85cc942
+oid sha256:bfb65fd55c64cfd5e67840830b799e7f2c73d9edc8118a2eafefb7abc1b9b7f0
 size 4856