kekunh
/

financial-twhin-bert-large-7labels

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [Twitter/twhin-bert-large](https://huggingface.co/Twitter/twhin-bert-large) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3040
-- Accuracy: 0.8968
-- F1: 0.8916
 ## Model description
@@ -46,18 +46,21 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 2
 ### Training results
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     |
-|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
-| 0.9592        | 0.3272 | 1500 | 0.6466          | 0.7665   | 0.7503 |
-| 0.4705        | 0.6545 | 3000 | 0.3785          | 0.8674   | 0.8528 |
-| 0.4196        | 0.9817 | 4500 | 0.5830          | 0.7892   | 0.7775 |
-| 0.3403        | 1.3089 | 6000 | 0.3683          | 0.8767   | 0.8728 |
-| 0.2962        | 1.6361 | 7500 | 0.3288          | 0.8889   | 0.8904 |
-| 0.272         | 1.9634 | 9000 | 0.3040          | 0.8968   | 0.8916 |
 ### Framework versions

 This model is a fine-tuned version of [Twitter/twhin-bert-large](https://huggingface.co/Twitter/twhin-bert-large) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.2960
+- Accuracy: 0.9023
+- F1: 0.9014
 ## Model description
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
 ### Training results
+| Training Loss | Epoch  | Step  | Validation Loss | Accuracy | F1     |
+|:-------------:|:------:|:-----:|:---------------:|:--------:|:------:|
+| 1.0082        | 0.3272 | 1500  | 0.4766          | 0.8302   | 0.8179 |
+| 0.4866        | 0.6545 | 3000  | 0.4327          | 0.8552   | 0.8395 |
+| 0.4354        | 0.9817 | 4500  | 0.3823          | 0.8616   | 0.8532 |
+| 0.3368        | 1.3089 | 6000  | 0.3435          | 0.8875   | 0.8787 |
+| 0.3136        | 1.6361 | 7500  | 0.3266          | 0.8872   | 0.8902 |
+| 0.2829        | 1.9634 | 9000  | 0.2997          | 0.8950   | 0.8939 |
+| 0.246         | 2.2906 | 10500 | 0.3183          | 0.8976   | 0.8923 |
+| 0.2277        | 2.6178 | 12000 | 0.3090          | 0.8994   | 0.8978 |
+| 0.2173        | 2.9450 | 13500 | 0.2960          | 0.9023   | 0.9014 |
 ### Framework versions

runs/May01_22-50-10_07010b723ec7/events.out.tfevents.1714603823.07010b723ec7.4808.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbbacce22c5d268742eac532f0b0239ba6c24772cb29075ae8f58aaf110a7ae2
-size 11133

 version https://git-lfs.github.com/spec/v1
+oid sha256:429a5dc1e294f0ddc72eec14c801f62761114c3697f729d2b59bde89fdad48d8
+size 11487