End of training

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: 3.2287
-- Accuracy: 0.1006
+- Loss: 1.8868
+- Accuracy: 0.5391
 
 ## Model description
 
@@ -44,16 +44,16 @@ 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: 3060
+- training_steps: 1216
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.9334        | 0.25  | 765  | 3.4929          | 0.0244   |
-| 2.3653        | 1.25  | 1530 | 3.3620          | 0.0511   |
-| 2.3702        | 2.25  | 2295 | 3.2735          | 0.1071   |
-| 2.199         | 3.25  | 3060 | 3.2287          | 0.1006   |
+| 1.2463        | 0.25  | 305  | 1.1609          | 0.6420   |
+| 1.2048        | 1.25  | 610  | 2.4836          | 0.3210   |
+| 0.9462        | 2.25  | 915  | 2.2188          | 0.5021   |
+| 1.2819        | 3.25  | 1216 | 1.8868          | 0.5391   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3be437c5e3a6dbe44630fd981a26624574f6d8fa7049bd7ef9a1e63a9c16ea20
+oid sha256:ab896728047fca1f48128d6c1a368b032965e305ad4b70af540526267c2294ac
 size 344943528

runs/Feb06_12-22-04_surveillance/events.out.tfevents.1707202329.surveillance.1444209.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb985251b7ad364c53fd747d378fbd39bdff670bde07ad50228b526bc3b8b52f
-size 20044
+oid sha256:76a6094ee9ff0c42fe8ccf636f1c824901b01d569c7663493b30bc98a31739ff
+size 25431