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: 1.2955
-- Accuracy: 0.5419
+- Loss: 0.8202
+- Accuracy: 0.25
 
 ## Model description
 
@@ -45,13 +45,13 @@ 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: 12
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.2724        | 1.0   | 300  | 1.1615          | 0.6429   |
+| 0.8867        | 1.0   | 12   | 0.8202          | 0.25     |
 
 
 ### Framework versions

runs/Sep24_15-29-51_stupa-ai/events.out.tfevents.1727191798.stupa-ai.2487498.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aca5374f78cb05229700f635c532508c8439e8b7ee70259582153a55687c0552
-size 5401
+oid sha256:937d27d6146eb7ce2b67dfc5e2279be0302242f05815a6d28ed0dd82cfaccc2d
+size 6066

runs/Sep24_15-29-51_stupa-ai/events.out.tfevents.1727191879.stupa-ai.2487498.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8cf4a7818c0caad5c042b7be7d0bf4052826fe75305d98469a82d4d6a27a459
+size 405