Model save

README.md

@@ -19,10 +19,10 @@ 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: 0.4966
-- F1: 0.5882
-- Roc Auc: 0.7540
-- Accuracy: 0.5556
+- Loss: 0.6007
+- F1: 0.6667
+- Roc Auc: 0.8095
+- Accuracy: 0.6667
 
 ## Model description
 
@@ -47,14 +47,15 @@ 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: 200
+- num_epochs: 300
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
-| 0.0246        | 79.0  | 790  | 0.6811          | 0.3529 | 0.6270  | 0.3333   |
-| 0.0667        | 158.0 | 1580 | 0.4966          | 0.5882 | 0.7540  | 0.5556   |
+| 0.0016        | 79.0  | 790  | 0.4859          | 0.6667 | 0.8095  | 0.6667   |
+| 0.0006        | 158.0 | 1580 | 0.5649          | 0.6667 | 0.8095  | 0.6667   |
+| 0.0004        | 237.0 | 2370 | 0.6007          | 0.6667 | 0.8095  | 0.6667   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd3b72d371d723733cbfc24bbe3ab59794446dc3ed071bf61208aed66945e346
+oid sha256:ab761659e01ec574018ce6421ceb73ee89ac0a70e663875d8aaf7d6add48e82b
 size 437977104

runs/Jan21_16-26-54_PingkeePC/events.out.tfevents.1737448018.PingkeePC

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a7622d279834248c076719d4b23f9d28e67d95c7864de5b5f6fef82268c8738
-size 8950
+oid sha256:6a88684ccedba17a712cf5da127afc912a3d098cd8afb2d5c8d09ac551c3fdff
+size 19639