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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4913
-- F1 Macro: 0.8637
-- F1: 0.9051
-- F1 Neg: 0.8223
-- Acc: 0.8762
-- Prec: 0.9094
-- Recall: 0.9008
-- Mcc: 0.7274
+- Loss: 0.7013
+- F1 Macro: 0.8811
+- F1: 0.9179
+- F1 Neg: 0.8442
+- Acc: 0.8925
+- Prec: 0.9179
+- Recall: 0.9179
+- Mcc: 0.7621
 
 ## Model description
 
@@ -51,7 +51,7 @@ The following hyperparameters were used during training:
 - distributed_type: multi-GPU
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results

runs/Mar10_13-52-14_tardis/events.out.tfevents.1710075391.tardis.10823.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394569cd2db2d3018587830fa795a1977d1de05c9fa72168c8abcb2c331637e7
+size 699