loha_fine_tuned_copa_sloberta

README.md

@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [EMBEDDIA/sloberta](https://huggingface.co/EMBEDDIA/sloberta) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6625
+- Loss: 0.6926
 - Accuracy: 0.6
-- F1: 0.6
+- F1: 0.6006
 
 ## Model description
 
@@ -40,7 +40,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.003
+- learning_rate: 2e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -52,14 +52,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.6991        | 1.0   | 50   | 0.6918          | 0.58     | 0.5810 |
-| 0.7015        | 2.0   | 100  | 0.6930          | 0.53     | 0.5310 |
-| 0.6965        | 3.0   | 150  | 0.6933          | 0.58     | 0.5807 |
-| 0.6971        | 4.0   | 200  | 0.6919          | 0.53     | 0.5312 |
-| 0.6953        | 5.0   | 250  | 0.6878          | 0.56     | 0.5575 |
-| 0.6775        | 6.0   | 300  | 0.6731          | 0.61     | 0.6108 |
-| 0.641         | 7.0   | 350  | 0.6595          | 0.62     | 0.6206 |
-| 0.597         | 8.0   | 400  | 0.6625          | 0.6      | 0.6    |
+| 0.6919        | 1.0   | 50   | 0.6925          | 0.6      | 0.6    |
+| 0.691         | 2.0   | 100  | 0.6926          | 0.6      | 0.6    |
+| 0.6924        | 3.0   | 150  | 0.6926          | 0.6      | 0.6    |
+| 0.6925        | 4.0   | 200  | 0.6927          | 0.6      | 0.6006 |
+| 0.6935        | 5.0   | 250  | 0.6926          | 0.6      | 0.6006 |
+| 0.694         | 6.0   | 300  | 0.6926          | 0.6      | 0.6006 |
+| 0.695         | 7.0   | 350  | 0.6926          | 0.6      | 0.6006 |
+| 0.6939        | 8.0   | 400  | 0.6926          | 0.6      | 0.6006 |
 
 
 ### Framework versions

adapter_config.json

@@ -18,6 +18,7 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "dense",
     "value",
     "query"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87f79ef324d57676f992144afa35392b916ae779fb0b6e5c5a70930dd1c9fbaa
-size 4735300
+oid sha256:c0ec4d0aaea3cb98714e61782cbb2516145a5a5c97c98014941dda0f4c7d6fec
+size 19108236

runs/May21_19-24-01_DESKTOP-22QTFDR/events.out.tfevents.1716312242.DESKTOP-22QTFDR.4484.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae2ddf0797f62d1c816014b73a45b416f97bda754eefe0c1bcaf45901ee04183
+size 9733

runs/May21_19-24-01_DESKTOP-22QTFDR/events.out.tfevents.1716312296.DESKTOP-22QTFDR.4484.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2158d1ebb33f58baa10ac310f3f423b1e819ade674c48a8a500bedb36341e079
+size 457

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56ed6506ef9e485f13374aede9c39741602f85bfd7d86563635b3c48d92c0773
+oid sha256:0aa4de4df14e3f66797279243d05a5b5edb24f5e8d72808c41e5b85f78de64aa
 size 5048