End of training

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7002
-- Accuracy: 0.48
+- Loss: 0.4047
+- Accuracy: 0.835
 
 ## Model description
 
@@ -38,20 +38,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 0.0002
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 63   | 0.7008          | 0.479    |
-| No log        | 2.0   | 126  | 0.7002          | 0.48     |
+| No log        | 1.0   | 125  | 0.6581          | 0.639    |
+| No log        | 2.0   | 250  | 0.5742          | 0.716    |
+| No log        | 3.0   | 375  | 0.4301          | 0.817    |
+| 0.5534        | 4.0   | 500  | 0.3904          | 0.837    |
+| 0.5534        | 5.0   | 625  | 0.4047          | 0.835    |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71d84ff0a2a5b77f060ece2a62d0ff02028244ac916c4319d74a5fcec6e0a57a
+oid sha256:65ce601e7b383573114023d5adf0b5a691d5ca84f64f8f928103c06bc57a858a
 size 162104

runs/Mar15_15-50-31_c9face729cf4/events.out.tfevents.1710517832.c9face729cf4.247.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:954cc1318f74f33f4676a725348b423e3d1aba330ac9005bb97c67f86eb880ee
-size 5676
+oid sha256:235a10a06052fb70bcb1d3982bd20b6f682a4c6b68393df304a95bc1a76849be
+size 6887