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: 0.4211
-- F1 Macro: 0.8908
-- F1: 0.9266
-- F1 Neg: 0.8550
-- Acc: 0.9025
-- Prec: 0.9389
-- Recall: 0.9145
-- Mcc: 0.7822
+- Loss: 0.4483
+- F1 Macro: 0.9009
+- F1: 0.9348
+- F1 Neg: 0.8669
+- Acc: 0.9125
+- Prec: 0.9366
+- Recall: 0.9331
+- Mcc: 0.8018
 
 ## 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    |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|
-| 0.5238        | 1.0   | 824  | 0.4772          | 0.8698   | 0.9062 | 0.8333 | 0.88   | 0.9062 | 0.9062 | 0.7396 |
-| 0.319         | 2.0   | 1648 | 0.4391          | 0.8940   | 0.9240 | 0.8641 | 0.9025 | 0.9222 | 0.9258 | 0.7881 |
-| 0.1949        | 3.0   | 2472 | 0.5378          | 0.8901   | 0.9231 | 0.8571 | 0.9    | 0.9091 | 0.9375 | 0.7811 |
+| 0.5215        | 1.0   | 824  | 0.3984          | 0.8854   | 0.9186 | 0.8521 | 0.895  | 0.9115 | 0.9258 | 0.7709 |
+| 0.3194        | 2.0   | 1648 | 0.4032          | 0.8978   | 0.9293 | 0.8664 | 0.9075 | 0.9101 | 0.9492 | 0.7973 |
+| 0.193         | 3.0   | 2472 | 0.4723          | 0.9037   | 0.9328 | 0.8746 | 0.9125 | 0.9170 | 0.9492 | 0.8085 |
 
 
 ### Framework versions

runs/Mar25_23-06-52_tardis/events.out.tfevents.1711404645.tardis.884395.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aedd6171e09612ce5109b1055483102f19a7a987dc8fb685187298a7eaf87546
+size 699