Model save

README.md

@@ -18,14 +18,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3963
-- F1 Macro: 0.9034
-- F1: 0.9403
-- F1 Neg: 0.8664
-- Acc: 0.9175
-- Prec: 0.9155
-- Recall: 0.9665
-- Mcc: 0.8102
+- Loss: 0.6785
+- F1 Macro: 0.8280
+- F1: 0.8929
+- F1 Neg: 0.7631
+- Acc: 0.8525
+- Prec: 0.8723
+- Recall: 0.9145
+- Mcc: 0.6583
 
 ## Model description
 
@@ -58,9 +58,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1     | F1 Neg | Acc    | Prec   | Recall | Mcc    |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|
-| 0.5951        | 1.0   | 947  | 0.5430          | 0.8465   | 0.8876 | 0.8055 | 0.8575 | 0.8964 | 0.8789 | 0.6933 |
-| 0.3947        | 2.0   | 1894 | 0.5327          | 0.8843   | 0.9234 | 0.8453 | 0.8975 | 0.8853 | 0.9648 | 0.7760 |
-| 0.2427        | 3.0   | 2841 | 0.5385          | 0.8824   | 0.9168 | 0.8481 | 0.8925 | 0.9080 | 0.9258 | 0.7652 |
+| 0.6384        | 1.0   | 835  | 0.5376          | 0.8057   | 0.8669 | 0.7445 | 0.825  | 0.8444 | 0.8906 | 0.6138 |
+| 0.4929        | 2.0   | 1670 | 0.6960          | 0.8014   | 0.8734 | 0.7294 | 0.8275 | 0.8235 | 0.9297 | 0.6170 |
+| 0.3293        | 3.0   | 2505 | 0.7225          | 0.8248   | 0.8805 | 0.7692 | 0.8425 | 0.8561 | 0.9062 | 0.6525 |
 
 
 ### Framework versions

runs/Mar27_10-07-06_tardis/events.out.tfevents.1711531727.tardis.3533496.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d5172f86c063879db7e77595ca5d65796227259dc7b641b55253f77b23aa1d8
+size 699