End of training

README.md

@@ -16,7 +16,7 @@ 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: 0.0537
+- Loss: 0.1396
 
 ## Model description
 
@@ -42,22 +42,18 @@ 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: 370
+- training_steps: 222
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.2132        | 0.1027 | 38   | 2.1570          |
-| 1.2007        | 1.1027 | 76   | 0.9905          |
-| 0.4869        | 2.1027 | 114  | 0.5075          |
-| 0.2626        | 3.1027 | 152  | 0.3664          |
-| 0.2857        | 4.1027 | 190  | 0.2793          |
-| 0.0597        | 5.1027 | 228  | 0.0692          |
-| 0.0116        | 6.1027 | 266  | 0.4589          |
-| 0.0091        | 7.1027 | 304  | 0.0480          |
-| 0.045         | 8.1027 | 342  | 0.0402          |
-| 0.0103        | 9.0757 | 370  | 0.0537          |
+| 2.1576        | 0.1712 | 38   | 1.9715          |
+| 1.1372        | 1.1712 | 76   | 0.8458          |
+| 0.4724        | 2.1712 | 114  | 0.4988          |
+| 0.2455        | 3.1712 | 152  | 0.2680          |
+| 0.0681        | 4.1712 | 190  | 0.1476          |
+| 0.0682        | 5.1441 | 222  | 0.1396          |
 
 
 ### Framework versions

runs/Sep24_20-48-44_18bbd82beced/events.out.tfevents.1727210925.18bbd82beced.7561.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80008d24dc02a5cf86c5f223be9f665972751e07d58c38b0f198831ef1a2fa8e
-size 11531
+oid sha256:617eb2089e9745981ac3d4756a5918c5d4caea9d7fbe512c22c8b933fcb13df0
+size 12156