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: 0.4379
-- F1 Macro: 0.9023
-- F1: 0.9375
-- F1 Neg: 0.8672
-- Acc: 0.915
-- Prec: 0.9273
-- Recall: 0.9480
-- Mcc: 0.8052
+- Loss: 0.5519
+- F1 Macro: 0.8624
+- F1: 0.9150
+- F1 Neg: 0.8097
+- Acc: 0.8825
+- Prec: 0.8908
+- Recall: 0.9405
+- Mcc: 0.7280
 
 ## 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    |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|
-| 0.5485        | 1.0   | 859  | 0.4785          | 0.8535   | 0.8898 | 0.8173 | 0.8625 | 0.9136 | 0.8672 | 0.7091 |
-| 0.3413        | 2.0   | 1718 | 0.4584          | 0.8927   | 0.9251 | 0.8602 | 0.9025 | 0.9094 | 0.9414 | 0.7864 |
-| 0.1912        | 3.0   | 2577 | 0.4596          | 0.8918   | 0.9216 | 0.8621 | 0.9    | 0.9252 | 0.9180 | 0.7837 |
+| 0.5605        | 1.0   | 835  | 0.4052          | 0.8129   | 0.8807 | 0.7451 | 0.8375 | 0.8304 | 0.9375 | 0.6402 |
+| 0.4662        | 2.0   | 1670 | 0.6216          | 0.8229   | 0.8818 | 0.7640 | 0.8425 | 0.8484 | 0.9180 | 0.6515 |
+| 0.3161        | 3.0   | 2505 | 0.6697          | 0.8360   | 0.8880 | 0.7839 | 0.8525 | 0.8635 | 0.9141 | 0.6748 |
 
 
 ### Framework versions

runs/Mar26_10-40-05_tardis/events.out.tfevents.1711447441.tardis.2260000.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c7b5cb0ab98abd33c62df560fcbfcc913ef19c2d3e51b403f1d41593c9a4d6
+size 699