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: 0.6658
-- Accuracy: 0.7871
+- Loss: 0.4709
+- Accuracy: 0.8333
 
 ## Model description
 
@@ -44,14 +44,14 @@ 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: 300
+- training_steps: 50
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.3617        | 0.5   | 150  | 1.3257          | 0.5      |
-| 0.7925        | 1.5   | 300  | 0.6653          | 0.7857   |
+| 0.7118        | 0.5   | 25   | 0.3528          | 1.0      |
+| 0.2012        | 1.5   | 50   | 0.3065          | 0.9167   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:804cc292088d283a224dcad786f56aa6184373d12b422917a193126f7b78877e
+oid sha256:aeee4826e549aec20a78f2a13875b8392b38e5eaf3d7715ea079ab583283122d
 size 344937368

runs/Jul02_19-27-25_c6d9a0630dcb/events.out.tfevents.1719948766.c6d9a0630dcb.4133.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd5da51d937fc95a2325178e7d4fb5553d3124fe0e30e3b6c529dcdb71c55b5
+size 405