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](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3142
-- Accuracy: 0.8857
+- Loss: 0.2626
+- Accuracy: 0.9143
 
 ## Model description
 
@@ -44,16 +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: 240
+- training_steps: 420
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.9673        | 0.25  | 60   | 1.7489          | 0.5      |
-| 1.0234        | 1.25  | 120  | 0.8390          | 0.7714   |
-| 0.3369        | 2.25  | 180  | 0.4395          | 0.8143   |
-| 0.2872        | 3.25  | 240  | 0.3142          | 0.8857   |
+| 0.3759        | 0.14  | 60   | 0.9304          | 0.7429   |
+| 0.3269        | 1.14  | 120  | 0.6277          | 0.8      |
+| 0.2179        | 2.14  | 180  | 0.4520          | 0.8143   |
+| 0.0438        | 3.14  | 240  | 1.2251          | 0.7286   |
+| 0.0638        | 4.14  | 300  | 0.3499          | 0.8857   |
+| 0.0047        | 5.14  | 360  | 0.2392          | 0.9143   |
+| 0.0039        | 6.14  | 420  | 0.2626          | 0.9143   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc8bc4f4465cc7a43a9b335e12c89accf7aa69dbf2df8c83c997cc550823ff2a
+oid sha256:03962255a482947cdbd3a66418ab91274b86b5496c6f9ff3115981fd473a8c81
 size 345003509