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: 0.8800
-- F1: 0.6471
+- Loss: 0.9376
+- F1: 0.6230
 
 ## 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   | 0.8709          | 0.7108 |
-| No log        | 1.25  | 46   | 0.8159          | 0.7108 |
-| No log        | 2.25  | 69   | 0.7319          | 0.7108 |
-| No log        | 3.25  | 92   | 0.7353          | 0.7108 |
+| 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 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b523990b432f14cef8eb1f15b71b2b9e4a5e7a918fa5c5e83406d3bfdfdeed4
+oid sha256:e59e749b72deb412f6b20891fa8bd4720ca31416d74c00a626445c2e5e928cd4
 size 344937368

runs/Nov16_12-35-50_eaf4bd5c128f/events.out.tfevents.1700139088.eaf4bd5c128f.124313.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2be20114713ed223a45fa3759f41ba699a66ffd448e423126d97f1f2d1e5a8c9
+size 399