ft-bert-with-swag

README.md

@@ -19,8 +19,8 @@ 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 the swag dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5507
-- Accuracy: 0.7844
+- Loss: 0.5656
+- Accuracy: 0.7797
 
 ## Model description
 
@@ -45,13 +45,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.7684        | 1.0   | 2299 | 0.5507          | 0.7844   |
+| 0.7503        | 1.0   | 2299 | 0.5656          | 0.7797   |
+| 0.3776        | 2.0   | 4598 | 0.5692          | 0.7986   |
+| 0.1457        | 3.0   | 6897 | 0.7690          | 0.8022   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3159ccd2024f9d908fa0cdac4df09bd211a3e25791281e755b4ed51ffe68589
+oid sha256:9fe48aaefdde8828f23a49f38757fe143c85d1ed5a591d4789b9933bf0407cb8
 size 437955572

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e044c3869b01d9743d93fa73c5f49408b3ec238e1778ec1156542654d74ea4cc
+oid sha256:4e375616bba3e8686b29ad6169332ed34c4ce95ee7fcd28bf401933b698532ee
 size 4155