jojoUla
/

bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR10-40

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [jojoUla/bert-large-cased-sigir-support-refute-no-label-40](https://huggingface.co/jojoUla/bert-large-cased-sigir-support-refute-no-label-40) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 5.8883
 ## Model description
@@ -39,53 +39,23 @@ 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: 40.0
 - mixed_precision_training: Native AMP
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 4.861         | 1.0   | 1    | 4.7030          |
-| 4.4676        | 2.0   | 2    | 6.2488          |
-| 7.1997        | 3.0   | 3    | 2.4042          |
-| 4.278         | 4.0   | 4    | 0.2763          |
-| 1.5949        | 5.0   | 5    | 3.1851          |
-| 1.2057        | 6.0   | 6    | 2.6029          |
-| 1.8272        | 7.0   | 7    | 0.0934          |
-| 1.8077        | 8.0   | 8    | 0.6277          |
-| 0.8089        | 9.0   | 9    | 0.5007          |
-| 1.5683        | 10.0  | 10   | 1.5534          |
-| 1.2161        | 11.0  | 11   | 1.0012          |
-| 0.8352        | 12.0  | 12   | 1.6421          |
-| 0.7029        | 13.0  | 13   | 1.7085          |
-| 0.9632        | 14.0  | 14   | 0.2879          |
-| 1.583         | 15.0  | 15   | 1.7979          |
-| 0.5708        | 16.0  | 16   | 0.5376          |
-| 0.467         | 17.0  | 17   | 1.9667          |
-| 0.3866        | 18.0  | 18   | 3.4478          |
-| 0.6           | 19.0  | 19   | 0.7479          |
-| 0.7362        | 20.0  | 20   | 0.2451          |
-| 1.5596        | 21.0  | 21   | 0.2730          |
-| 0.4868        | 22.0  | 22   | 0.3584          |
-| 0.5333        | 23.0  | 23   | 1.3786          |
-| 0.2568        | 24.0  | 24   | 1.6088          |
-| 1.3369        | 25.0  | 25   | 0.7165          |
-| 0.425         | 26.0  | 26   | 1.8231          |
-| 0.1444        | 27.0  | 27   | 0.2272          |
-| 0.2839        | 28.0  | 28   | 0.0720          |
-| 0.1631        | 29.0  | 29   | 0.4542          |
-| 1.2894        | 30.0  | 30   | 0.3767          |
-| 0.3602        | 31.0  | 31   | 1.0501          |
-| 0.3226        | 32.0  | 32   | 0.2222          |
-| 0.172         | 33.0  | 33   | 0.1084          |
-| 0.6193        | 34.0  | 34   | 0.3281          |
-| 0.5723        | 35.0  | 35   | 1.4412          |
-| 0.1678        | 36.0  | 36   | 0.1331          |
-| 0.3903        | 37.0  | 37   | 0.9474          |
-| 0.0966        | 38.0  | 38   | 0.6377          |
-| 0.19          | 39.0  | 39   | 1.8760          |
-| 0.3088        | 40.0  | 40   | 0.1489          |
 ### Framework versions

 This model is a fine-tuned version of [jojoUla/bert-large-cased-sigir-support-refute-no-label-40](https://huggingface.co/jojoUla/bert-large-cased-sigir-support-refute-no-label-40) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 2.8726
 ## Model description
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 10.0
 - mixed_precision_training: Native AMP
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 3.3922        | 1.0   | 1    | 7.7770          |
+| 5.775         | 2.0   | 2    | 7.9736          |
+| 7.0239        | 3.0   | 3    | 5.2036          |
+| 4.0829        | 4.0   | 4    | 2.9272          |
+| 3.4724        | 5.0   | 5    | 5.9639          |
+| 2.5963        | 6.0   | 6    | 3.5008          |
+| 3.4139        | 7.0   | 7    | 2.1127          |
+| 2.5872        | 8.0   | 8    | 3.6687          |
+| 2.9188        | 9.0   | 9    | 3.8722          |
+| 1.62          | 10.0  | 10   | 2.6152          |
 ### Framework versions