aminfoweb/classification_test_27Dec

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2892
-- Accuracy: 0.9508
+- Loss: 0.3279
+- Accuracy: 0.9493
 
 ## Model description
 
@@ -43,17 +43,19 @@ 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: 5
+- num_epochs: 7
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.5775        | 1.0   | 3750  | 0.6166          | 0.902    |
-| 0.3579        | 2.0   | 7500  | 0.4535          | 0.9228   |
-| 0.2818        | 3.0   | 11250 | 0.4030          | 0.9336   |
-| 0.1849        | 4.0   | 15000 | 0.3642          | 0.9408   |
-| 0.0957        | 5.0   | 18750 | 0.2892          | 0.9508   |
+| 0.4495        | 1.0   | 5293  | 0.6105          | 0.8841   |
+| 0.2916        | 2.0   | 10586 | 0.4680          | 0.9294   |
+| 0.3098        | 3.0   | 15879 | 0.4065          | 0.9419   |
+| 0.2335        | 4.0   | 21172 | 0.3796          | 0.9430   |
+| 0.1565        | 5.0   | 26465 | 0.3467          | 0.9428   |
+| 0.1886        | 6.0   | 31758 | 0.3174          | 0.9487   |
+| 0.1042        | 7.0   | 37051 | 0.3279          | 0.9493   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9745ca467e828a36020bdba668d344b7052a21c053762e20b95c46634b552cb
+oid sha256:cbca3c21e88d2370da4a7ae5c3e175070b13a1a44edb3d5dd3e3a950d05be939
 size 594699716