Model save

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: 0.9376
-- F1: 0.6230
+- Loss: 0.7345
+- F1: 0.7429
 
 ## Model description
 
@@ -50,10 +50,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| No log        | 0.25  | 23   | 0.8954          | 0.7188 |
-| No log        | 1.25  | 46   | 0.8061          | 0.7188 |
-| No log        | 2.25  | 69   | 0.7607          | 0.7188 |
-| No log        | 3.25  | 92   | 0.7474          | 0.7188 |
+| No log        | 0.25  | 23   | 0.6788          | 0.8235 |
+| No log        | 1.25  | 46   | 0.6501          | 0.8235 |
+| No log        | 2.25  | 69   | 0.6339          | 0.8235 |
+| No log        | 3.25  | 92   | 0.6372          | 0.8235 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:475b04817c707c0116d6014c5516a4bb78c230058e1af644e5492e0ff0fdff02
+oid sha256:6d4deab9c0c4488f4ec2f53c891dc7a29e24f6e2cee39d56fc8cbfe47807c9ab
 size 344937368

runs/Nov16_13-02-47_eaf4bd5c128f/events.out.tfevents.1700140826.eaf4bd5c128f.131373.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:946db865f99a045b9693cd8c67a25fb93692befd7b9a7216f2db09258c933849
+size 399