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: 2.8849
-- Accuracy: 0.3
+- Loss: 3.4002
+- Accuracy: 0.1190
 
 ## Model description
 
@@ -44,16 +44,20 @@ 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: 20
+- training_steps: 80
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.25  | 5    | 2.9612          | 0.1      |
-| 3.1119        | 1.25  | 10   | 2.9466          | 0.1      |
-| 3.1119        | 2.25  | 15   | 2.9071          | 0.2      |
-| 2.908         | 3.25  | 20   | 2.8849          | 0.3      |
+| 3.8439        | 0.14  | 11   | 3.6563          | 0.0714   |
+| 3.8227        | 1.14  | 22   | 3.6419          | 0.0476   |
+| 3.7396        | 2.14  | 33   | 3.5863          | 0.0952   |
+| 3.6939        | 3.14  | 44   | 3.5431          | 0.0952   |
+| 3.5364        | 4.14  | 55   | 3.4718          | 0.1190   |
+| 3.508         | 5.14  | 66   | 3.4199          | 0.1190   |
+| 3.5206        | 6.14  | 77   | 3.4016          | 0.1190   |
+| 3.425         | 7.04  | 80   | 3.4002          | 0.1190   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1266365eb4094d681c3200d3341d7a1db6ea0560f7be75eb09c3add667847a94
+oid sha256:f55028a0fa146155a218af6eac1d00edd5322cf0a8b8b9afff3ca28e3ab25f85
 size 345093237