minoosh
/

finetuned_bert-base-uncased

@@ -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: 1.0293
-- Accuracy: 0.6664
 ## Model description
@@ -42,32 +42,27 @@ 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: 20
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 204  | 1.0807          | 0.6586   |
-| No log        | 2.0   | 408  | 1.2250          | 0.6760   |
-| 0.271         | 3.0   | 612  | 1.1975          | 0.6663   |
-| 0.271         | 4.0   | 816  | 1.2170          | 0.6625   |
-| 0.2395        | 5.0   | 1020 | 1.2817          | 0.6702   |
-| 0.2395        | 6.0   | 1224 | 1.4138          | 0.6634   |
-| 0.2395        | 7.0   | 1428 | 1.5268          | 0.6819   |
-| 0.1661        | 8.0   | 1632 | 1.5753          | 0.6702   |
-| 0.1661        | 9.0   | 1836 | 1.6794          | 0.6663   |
-| 0.1349        | 10.0  | 2040 | 1.6416          | 0.6731   |
-| 0.1349        | 11.0  | 2244 | 1.7056          | 0.6741   |
-| 0.1349        | 12.0  | 2448 | 1.7374          | 0.6760   |
-| 0.1159        | 13.0  | 2652 | 1.8817          | 0.6644   |
-| 0.1159        | 14.0  | 2856 | 1.7318          | 0.6751   |
-| 0.111         | 15.0  | 3060 | 1.8213          | 0.6712   |
-| 0.111         | 16.0  | 3264 | 1.8347          | 0.6722   |
-| 0.111         | 17.0  | 3468 | 1.8072          | 0.6780   |
-| 0.0988        | 18.0  | 3672 | 1.8371          | 0.6770   |
-| 0.0988        | 19.0  | 3876 | 1.8562          | 0.6741   |
-| 0.0907        | 20.0  | 4080 | 1.8583          | 0.6741   |
 ### Framework versions

 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: 0.9064
+- Accuracy: 0.6591
 ## Model description
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 15
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 204  | 0.9670          | 0.6052   |
+| No log        | 2.0   | 408  | 0.8899          | 0.6731   |
+| 0.8476        | 3.0   | 612  | 0.9283          | 0.6722   |
+| 0.8476        | 4.0   | 816  | 1.0110          | 0.6828   |
+| 0.3419        | 5.0   | 1020 | 1.0947          | 0.6741   |
+| 0.3419        | 6.0   | 1224 | 1.1896          | 0.6799   |
+| 0.3419        | 7.0   | 1428 | 1.3467          | 0.6887   |
+| 0.193         | 8.0   | 1632 | 1.3716          | 0.6838   |
+| 0.193         | 9.0   | 1836 | 1.4742          | 0.6809   |
+| 0.1485        | 10.0  | 2040 | 1.5121          | 0.6867   |
+| 0.1485        | 11.0  | 2244 | 1.5670          | 0.6819   |
+| 0.1485        | 12.0  | 2448 | 1.5593          | 0.6867   |
+| 0.1185        | 13.0  | 2652 | 1.6455          | 0.6809   |
+| 0.1185        | 14.0  | 2856 | 1.6417          | 0.6877   |
+| 0.1077        | 15.0  | 3060 | 1.6399          | 0.6867   |
 ### Framework versions