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: 0.4078
-- F1 Macro: 0.8882
-- F1: 0.9264
-- F1 Neg: 0.8501
-- Acc: 0.9012
-- Prec: 0.9053
-- Recall: 0.9485
-- Mcc: 0.7787
+- Loss: 0.5316
+- F1 Macro: 0.8888
+- F1: 0.9241
+- F1 Neg: 0.8535
+- Acc: 0.9
+- Prec: 0.9189
+- Recall: 0.9294
+- Mcc: 0.7777
 
 ## 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/Mar12_12-11-09_tardis/events.out.tfevents.1710242128.tardis.115115.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64cab33e65a5b7265934df9b4e0dae63093a790556541d994fd92d87690e23ce
+size 699