End of training

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5254
-- Accuracy: 0.758
-- F1: 0.8197
+- Loss: 0.7373
+- Accuracy: 0.714
+- F1: 0.7866
 
 ## Model description
 
@@ -45,15 +45,17 @@ 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: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.6356        | 1.0   | 751  | 0.5375          | 0.742    | 0.8206 |
-| 0.5926        | 2.0   | 1502 | 0.5102          | 0.769    | 0.8310 |
-| 0.5533        | 3.0   | 2253 | 0.5254          | 0.758    | 0.8197 |
+| 0.6292        | 1.0   | 751  | 0.5615          | 0.732    | 0.8154 |
+| 0.5615        | 2.0   | 1502 | 0.5663          | 0.745    | 0.8188 |
+| 0.4986        | 3.0   | 2253 | 0.5709          | 0.74     | 0.7969 |
+| 0.4214        | 4.0   | 3004 | 0.7008          | 0.714    | 0.7963 |
+| 0.3636        | 5.0   | 3755 | 0.7373          | 0.714    | 0.7866 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77ff9ad100a570e2de8510e5b6dd8d21d6093c1d5d11e9602ae91094c7b82baf
+oid sha256:574c7db218fe7a142fb2c84444cc596b57b13c2bb803d85ec64789007ae8db7b
 size 1340710193

runs/Jul22_06-33-54_b007f2cd612f/events.out.tfevents.1690008016.b007f2cd612f.590.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caf5b1625ab8aca5ae8a88ed1b540b842283d36bf33b60e1ce539b9ef6c1109c
-size 6737
+oid sha256:ba13202c3d10b55d620154bd0f09395fdad6a16f9c84a8b446ed59a9f705631b
+size 7460