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: 0.4605
-- F1 Macro: 0.8743
-- F1: 0.9169
-- F1 Neg: 0.8318
+- Loss: 0.5119
+- F1 Macro: 0.8755
+- F1: 0.9161
+- F1 Neg: 0.8349
 - Acc: 0.8888
-- Prec: 0.8976
-- Recall: 0.9370
-- Mcc: 0.7505
+- Prec: 0.9050
+- Recall: 0.9275
+- Mcc: 0.7516
 
 ## 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_12-06-47_tardis/events.out.tfevents.1710241864.tardis.115115.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c99baecc4675df6c7ede1a7cd12e37af7e43a98f0bd5c40cb3a61082ea134425
+size 699