End of training

README.md

@@ -17,8 +17,8 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0113
-- Accuracy: 0.9984
+- Loss: 0.0164
+- Accuracy: 0.9957
 
 ## Model description
 
@@ -49,14 +49,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 313  | 0.2754          | 0.9224   |
-| 0.5403        | 2.0   | 626  | 0.0468          | 0.9864   |
-| 0.5403        | 3.0   | 939  | 0.0113          | 0.9984   |
+| No log        | 1.0   | 376  | 0.2186          | 0.9301   |
+| 0.568         | 2.0   | 752  | 0.0361          | 0.9903   |
+| 0.1363        | 3.0   | 1128 | 0.0164          | 0.9957   |
 
 
 ### Framework versions
 
 - Transformers 4.35.2
-- Pytorch 2.1.0+cu118
+- Pytorch 2.1.0+cu121
 - Datasets 2.15.0
 - Tokenizers 0.15.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:320e60f71d2d4f205c460502e621c4688d4f5cfbed29181f8632407ca12cf73d
+oid sha256:0c434d039789f4f26678f95ba17905e17906eaffdc2435943c86eb7f15bc1f0a
 size 437955572

runs/Dec15_18-46-08_2d885f8f60fc/events.out.tfevents.1702665969.2d885f8f60fc.7012.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d759d5cee26bbc7b6cca8bac2e22fcac281a200d125a762909fb6b8c9d909b
-size 5194
+oid sha256:38a4ca942d7c573ca937c4f79cfbdd1b37d217805ee65b734d420163ff6dfc20
+size 5871