Final model pretrained on the greek-longformer after 6 epochs

README.md

@@ -16,8 +16,8 @@ model-index:
 This model is a second-stage pretrained version of [dimitriz/greek-longformer-base-4096](https://huggingface.co/dimitriz/greek-longformer-base-4096) trained on the [dimitriz/greek_media_texts](https://huggingface.co/datasets/dimitriz/greek_media_texts) dataset.
 It achieves the following results on the evaluation set:
 
-- Loss: 1.1910
-- Accuracy: 0.7482
+- Loss: 1.1424
+- Accuracy: 0.7574
 
 ## Model description
 
@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3.0
+- num_epochs: 6.0
 
 ### Training results
 

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bb69f67126e7771b15767ea1eac076420a61bd8a2e33fdf2eb8ef380f45403b
+oid sha256:5a3b3c6de7a827ceb0a0bbdad46ec13b2947c7a16298b99992684c3bde41005b
 size 600280789

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae841c3dfdaef7605e51056105c3d361313b0140ec7d15788da2133c3b45f9d7
+oid sha256:310b1d7261be97fe835e247952ea52019b57a28c3ccfbe81f55cfea38279964f
 size 600313080