ahmedr996
/

videomae-base-finetuned-soccer

Video Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

ahmedr996 commited on 6 days ago

Commit

a5ea1c7

·

verified ·

1 Parent(s): 44ff31d

Model save

Files changed (2) hide show

README.md +13 -13
model.safetensors +1 -1

README.md CHANGED Viewed

@@ -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: 0.5665
-- Accuracy: 0.75
 ## Model description
@@ -45,20 +45,20 @@ The following hyperparameters were used during training:
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 96
 ### Training results
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
-|:-------------:|:------:|:----:|:---------------:|:--------:|
-| 1.018         | 1.0    | 13   | 0.9591          | 0.5      |
-| 0.8837        | 2.0    | 26   | 1.0248          | 0.5833   |
-| 0.7304        | 3.0    | 39   | 0.9565          | 0.5      |
-| 0.6652        | 4.0    | 52   | 0.7661          | 0.5833   |
-| 0.4719        | 5.0    | 65   | 0.9185          | 0.6667   |
-| 0.5202        | 6.0    | 78   | 0.7269          | 0.6667   |
-| 0.3601        | 7.0    | 91   | 0.5654          | 0.75     |
-| 0.3601        | 7.3846 | 96   | 0.5665          | 0.75     |
 ### Framework versions

 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: 0.9822
+- Accuracy: 0.5
 ## Model description
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
+- training_steps: 24
 ### Training results
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 3    | 1.0756          | 0.4167   |
+| No log        | 2.0   | 6    | 1.0862          | 0.4167   |
+| No log        | 3.0   | 9    | 1.0376          | 0.5      |
+| 1.126         | 4.0   | 12   | 0.9851          | 0.6667   |
+| 1.126         | 5.0   | 15   | 0.9839          | 0.5      |
+| 1.126         | 6.0   | 18   | 0.9849          | 0.5      |
+| 0.8186        | 7.0   | 21   | 0.9838          | 0.5833   |
+| 0.8186        | 8.0   | 24   | 0.9822          | 0.5      |
 ### Framework versions

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdb90bb2a29717ca83cc8d0b9dcd4d8f197a3a7d9bdb4fa9b8ef2b90371364e3
 size 344940444

 version https://git-lfs.github.com/spec/v1
+oid sha256:1887c708be646eb55316f61c068a040aaea1e5544f09f6b8c34e1dcc3efc5008
 size 344940444