Training in progress, epoch 1

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6400
-- Accuracy: 0.7389
+- Loss: 0.4773
+- Accuracy: 0.7981
 
 ## Model description
 
@@ -42,15 +42,14 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.5488        | 1.0   | 1230 | 0.5486          | 0.7194   |
-| 0.4161        | 2.0   | 2460 | 0.5310          | 0.7519   |
-| 0.2961        | 3.0   | 3690 | 0.6400          | 0.7389   |
+| 0.5683        | 1.0   | 840  | 0.4790          | 0.7814   |
+| 0.3602        | 2.0   | 1680 | 0.4773          | 0.7981   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5843efee4da980e44209ae844236c64327f9b2d36470d7a27ef5ee2614c99721
+oid sha256:6dca3cc2d5e609aed2c8c39979599b508cbe670fbaea79331ce15c79c89fb6ae
 size 438007925

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9507b4e11dc632c8f83e2dfc38639a8e9acf9aa6f56b47f9da93048056367d8
+oid sha256:8048a625f267c73d2dcf7c226fca7682aa0be57a808f444b2c676ab434062a1b
 size 3451