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-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5058
-- F1 Macro: 0.8727
-- F1: 0.9080
-- F1 Neg: 0.8374
-- Acc: 0.8825
-- Prec: 0.928
-- Recall: 0.8889
-- Mcc: 0.7469
+- Loss: 0.4619
+- F1 Macro: 0.8956
+- F1: 0.9308
+- F1 Neg: 0.8604
+- Acc: 0.9075
+- Prec: 0.9361
+- Recall: 0.9257
+- Mcc: 0.7913
 
 ## 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    |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|
-| 0.5703        | 1.0   | 1681 | 0.5408          | 0.8014   | 0.8717 | 0.7311 | 0.8263 | 0.8237 | 0.9255 | 0.6155 |
-| 0.4812        | 2.0   | 3362 | 0.5507          | 0.8373   | 0.8910 | 0.7836 | 0.855  | 0.8556 | 0.9294 | 0.6808 |
-| 0.3558        | 3.0   | 5043 | 0.6018          | 0.8481   | 0.8906 | 0.8056 | 0.86   | 0.8872 | 0.8941 | 0.6962 |
+| 0.551         | 1.0   | 824  | 0.4409          | 0.8273   | 0.8826 | 0.7721 | 0.845  | 0.8566 | 0.9102 | 0.6579 |
+| 0.4251        | 2.0   | 1648 | 0.6715          | 0.8083   | 0.8893 | 0.7273 | 0.8425 | 0.8083 | 0.9883 | 0.6651 |
+| 0.342         | 3.0   | 2472 | 0.5680          | 0.8681   | 0.9077 | 0.8286 | 0.88   | 0.8939 | 0.9219 | 0.7371 |
 
 
 ### Framework versions

runs/Mar26_08-46-00_tardis/events.out.tfevents.1711439477.tardis.895130.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46f804e0a1f77596fef75a2c06c768e5b05ccf4d7cc605fb1f2c249b97e7a623
+size 699