End of training

README.md

@@ -18,7 +18,7 @@ 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: 0.9326
+- Loss: 0.8608
 - Accuracy: 0.6018
 
 ## Model description
@@ -45,16 +45,14 @@ 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: 132
+- training_steps: 66
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 0.6231        | 0.2576 | 34   | 0.7837          | 0.6018   |
-| 0.5601        | 1.2576 | 68   | 0.7498          | 0.6018   |
-| 0.4906        | 2.2576 | 102  | 0.8761          | 0.6018   |
-| 0.6457        | 3.2273 | 132  | 0.9326          | 0.6018   |
+| 0.6068        | 0.5152 | 34   | 0.7880          | 0.6018   |
+| 0.5232        | 1.4848 | 66   | 0.8608          | 0.6018   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eed26e533406364ba66df7bb865b0443394a5618248531f97c4964727fc398f
+oid sha256:05ceeb2a92442996912d307cd0ca36b9db33689f88dad57658c161554d5e2096
 size 344937368