fine_tuned_copa_bert

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6931
-- Accuracy: 0.55
-- F1: 0.3903
+- Loss: 1.0295
+- Accuracy: 0.54
+- F1: 0.5407
 
 ## Model description
 
@@ -39,7 +39,7 @@ 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
@@ -51,14 +51,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.7002        | 1.0   | 50   | 0.6931          | 0.52     | 0.3763 |
-| 0.7122        | 2.0   | 100  | 0.6931          | 0.57     | 0.5334 |
-| 0.7061        | 3.0   | 150  | 0.6931          | 0.55     | 0.4368 |
-| 0.704         | 4.0   | 200  | 0.6931          | 0.53     | 0.3810 |
-| 0.722         | 5.0   | 250  | 0.6931          | 0.55     | 0.3903 |
-| 0.7157        | 6.0   | 300  | 0.6931          | 0.53     | 0.4831 |
-| 0.7265        | 7.0   | 350  | 0.6931          | 0.48     | 0.4457 |
-| 0.7298        | 8.0   | 400  | 0.6931          | 0.55     | 0.3903 |
+| 0.7066        | 1.0   | 50   | 0.6907          | 0.54     | 0.5411 |
+| 0.6897        | 2.0   | 100  | 0.6880          | 0.57     | 0.5709 |
+| 0.6001        | 3.0   | 150  | 0.7025          | 0.55     | 0.5511 |
+| 0.4629        | 4.0   | 200  | 0.7810          | 0.53     | 0.5310 |
+| 0.3402        | 5.0   | 250  | 1.0003          | 0.55     | 0.5511 |
+| 0.2299        | 6.0   | 300  | 1.0220          | 0.55     | 0.5511 |
+| 0.1874        | 7.0   | 350  | 0.9956          | 0.56     | 0.5611 |
+| 0.1133        | 8.0   | 400  | 1.0295          | 0.54     | 0.5407 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89620eec3a6ad5b0404101f264de367279bd096067a2eaf6aa45479f70685209
+oid sha256:18eace404a6d6ae1fcd54d192ea4cd2b2ca9fe6cb8f63ce5211becb6ede4f36e
 size 437955572

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:163f535241f470a1250bd9411edec67ae67962b2a0cdcc8efb4bf142a0baa9cc
+oid sha256:ed42acd8eb5948a8023b077b19eac2e36b049e25cec4f25461538ac66ad21e12
 size 4984