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: 0.4154
-- Accuracy: 0.8857
+- Loss: 0.1179
+- Accuracy: 0.9754
 
 ## 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: 148
+- training_steps: 184
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 2.1542        | 0.2568 | 38   | 1.8921          | 0.2857   |
-| 1.1105        | 1.2568 | 76   | 0.9155          | 0.6857   |
-| 0.5273        | 2.2568 | 114  | 0.5447          | 0.8      |
-| 0.3606        | 3.2297 | 148  | 0.4154          | 0.8857   |
+| 0.4232        | 0.2554 | 47   | 0.9096          | 0.6523   |
+| 0.0693        | 1.2554 | 94   | 0.0388          | 0.9862   |
+| 0.0005        | 2.2554 | 141  | 0.1113          | 0.9769   |
+| 0.0005        | 3.2337 | 184  | 0.1179          | 0.9754   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6079da6e52075dc9608d452dfff33214908958b6434bb9c1ba8c37cd38a67c6
+oid sha256:28f65014b0e33ec03627cff7f1e092cc8b5fd4fa30936918246b07be9f5a7740
 size 344937368

runs/May09_18-47-07_scale/events.out.tfevents.1715280428.scale

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b16e6aea3bc714895ca0a77e1f94bc2d68cba24638f1ebd57777391eed2b2bb
-size 8446
+oid sha256:f3478bc00e3390faa1cfe89b3d0315d5dec8aefac77dd89862df0fb27e289f2e
+size 10290