2nzi
/

videomae-surf-analytics

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7527
-- Accuracy: 0.6364
 ## Model description
@@ -44,14 +44,15 @@ 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
-- training_steps: 74
 ### Training results
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 0.6252        | 0.5135 | 38   | 0.6596          | 0.6182   |
-| 0.5187        | 1.4865 | 74   | 0.7527          | 0.6364   |
 ### Framework versions

 This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.5940
+- Accuracy: 0.8636
 ## Model description
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
+- training_steps: 555
 ### Training results
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.8667        | 0.3351 | 186  | 0.9741          | 0.5727   |
+| 0.8111        | 1.3351 | 372  | 0.8580          | 0.7364   |
+| 0.4008        | 2.3297 | 555  | 0.5940          | 0.8636   |
 ### Framework versions

runs/May17_01-25-40_MSI/events.out.tfevents.1715919261.MSI.2780.1 ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:63da84f249b40f5cf597256b365246b4793ebfefe86ba6184a7ad2762ed87b43
+size 1380