End of training

README.md

@@ -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-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-base-finetuned-kinetics) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0050
-- Accuracy: 1.0
+- Loss: 0.6776
+- Accuracy: 0.85
 
 ## Model description
 
@@ -44,19 +44,19 @@ 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: 84
+- training_steps: 119
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.7059        | 0.15  | 13   | 0.5431          | 0.8889   |
-| 0.4596        | 1.15  | 26   | 0.3715          | 0.7778   |
-| 0.234         | 2.15  | 39   | 0.1132          | 0.8889   |
-| 0.1727        | 3.15  | 52   | 0.0878          | 1.0      |
-| 0.2124        | 4.15  | 65   | 0.0079          | 1.0      |
-| 0.0387        | 5.15  | 78   | 0.0051          | 1.0      |
-| 0.022         | 6.07  | 84   | 0.0050          | 1.0      |
+| 0.6226        | 0.15  | 18   | 0.5180          | 0.8      |
+| 0.3479        | 1.15  | 36   | 0.8291          | 0.8      |
+| 0.4482        | 2.15  | 54   | 0.7873          | 0.85     |
+| 0.1432        | 3.15  | 72   | 0.8196          | 0.8      |
+| 0.216         | 4.15  | 90   | 0.8239          | 0.85     |
+| 0.1211        | 5.15  | 108  | 0.6926          | 0.85     |
+| 0.02          | 6.09  | 119  | 0.6776          | 0.85     |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44b98927f614e18e8942ea717a8012cd7a971ac4bb34f3f6d74872c9e3156736
+oid sha256:03b788eb767c8dc6ef2f403e692e18355951c82821892160fb75770c886c262a
 size 344978933