sungkwan2/my_awesome_video_cls_model

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: 1.1976
-- Accuracy: 0.6143
+- Loss: 1.2231
+- Accuracy: 0.6
 
 ## Model description
 
@@ -52,7 +52,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.0507        | 1.0   | 300  | 1.1976          | 0.6143   |
+| 1.0035        | 1.0   | 300  | 1.2231          | 0.6      |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40b3e6353bd207060c49b25781e8d3f034929f5860f1a010b0082e306be4f97d
+oid sha256:24300aaeb1fb12eabfef80b6e70475e8a19e42fb193712f3bd081f812f5d50f5
 size 344961984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7595ee9c99a97568ee09a8c229b649c6c78b57e52906bedbcfec8c3584cdc92d
+oid sha256:ee0d5c04527f0d98d9a4877a0fc91b33ebb81b9cfd8d7c3248f5cbde0322c24a
 size 5777