Model save

README.md

@@ -18,8 +18,8 @@ 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: 0.4497
-- Accuracy: 0.8774
+- Loss: 0.5545
+- Accuracy: 0.8
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 2.1243        | 0.2568 | 38   | 1.8105          | 0.3857   |
-| 0.9539        | 1.2568 | 76   | 0.9815          | 0.5857   |
-| 0.4701        | 2.2568 | 114  | 0.4805          | 0.8571   |
-| 0.2869        | 3.2297 | 148  | 0.3917          | 0.8714   |
+| 0.2895        | 0.2568 | 38   | 0.4604          | 0.8429   |
+| 0.0817        | 1.2568 | 76   | 0.2629          | 0.9429   |
+| 0.0437        | 2.2568 | 114  | 0.1733          | 0.9143   |
+| 0.0516        | 3.2297 | 148  | 0.1426          | 0.9429   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89fbf339868f0b4e27f175ca7245916e929b3d32f36386e229ad8d87e7a5e322
+oid sha256:c8eca535bf55576487fae14f29832d26f0c4db0969c89d1b711479c12e609ae9
 size 344961984

runs/Oct14_14-08-54_dc6088e9f91b/events.out.tfevents.1728914950.dc6088e9f91b.3595.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c2761407b41a3a981cca5a9b686876fdb4a5038af184358b60836d18a31c591
-size 9519
+oid sha256:8564b4e5ca8f7f36a053fe79f70b7bb91b0f2e62bc928dab091e0c4a852147bf
+size 10196

runs/Oct14_14-08-54_dc6088e9f91b/events.out.tfevents.1728915192.dc6088e9f91b.3595.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e71ad76ae093d5c2ac07008252716899f41ac36413eea21485316e855cb7ddf
+size 411