asmaa1
/

videomae-base-finetuned-SLT-subset

@@ -17,7 +17,7 @@ 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: 0.3217
 - Accuracy: 1.0
 ## Model description
@@ -44,28 +44,28 @@ 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: 960
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 3.9388        | 0.06  | 61   | 3.6928          | 0.0244   |
-| 3.922         | 1.06  | 122  | 3.7470          | 0.0244   |
-| 3.8564        | 2.06  | 183  | 3.5744          | 0.0488   |
-| 3.8           | 3.06  | 244  | 3.4795          | 0.0732   |
-| 3.6299        | 4.06  | 305  | 3.4226          | 0.0732   |
-| 3.7411        | 5.06  | 366  | 3.3728          | 0.0732   |
-| 3.4738        | 6.06  | 427  | 3.2456          | 0.0732   |
-| 3.3784        | 7.06  | 488  | 2.8674          | 0.5610   |
-| 2.9917        | 8.06  | 549  | 2.2194          | 0.7073   |
-| 2.1432        | 9.06  | 610  | 1.4439          | 0.8780   |
-| 1.377         | 10.06 | 671  | 1.0637          | 0.9512   |
-| 1.1721        | 11.06 | 732  | 0.7384          | 0.9512   |
-| 0.8749        | 12.06 | 793  | 0.4955          | 1.0      |
-| 0.4729        | 13.06 | 854  | 0.3995          | 1.0      |
-| 0.4317        | 14.06 | 915  | 0.3367          | 1.0      |
-| 0.3025        | 15.05 | 960  | 0.3217          | 1.0      |
 ### 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: 0.1513
 - Accuracy: 1.0
 ## Model description
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
+- training_steps: 944
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 3.9224        | 0.06  | 59   | 3.7150          | 0.025    |
+| 3.9538        | 1.06  | 118  | 3.7131          | 0.025    |
+| 3.8824        | 2.06  | 177  | 3.6952          | 0.025    |
+| 3.8135        | 3.06  | 236  | 3.6851          | 0.05     |
+| 3.8444        | 4.06  | 295  | 3.6689          | 0.025    |
+| 3.7715        | 5.06  | 354  | 3.6183          | 0.05     |
+| 3.6616        | 6.06  | 413  | 3.4405          | 0.4      |
+| 3.6175        | 7.06  | 472  | 3.0778          | 0.325    |
+| 3.1062        | 8.06  | 531  | 2.0972          | 0.75     |
+| 1.8942        | 9.06  | 590  | 1.2638          | 0.925    |
+| 1.3975        | 10.06 | 649  | 0.7811          | 0.975    |
+| 1.0269        | 11.06 | 708  | 0.4473          | 1.0      |
+| 0.3623        | 12.06 | 767  | 0.3073          | 1.0      |
+| 0.3611        | 13.06 | 826  | 0.2007          | 1.0      |
+| 0.1881        | 14.06 | 885  | 0.1614          | 1.0      |
+| 0.1773        | 15.06 | 944  | 0.1513          | 1.0      |
 ### Framework versions

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d02409733d604e1b8554800bf47ff626a38148c550e5227dc154a4d3239b8fc
 size 345095797

 version https://git-lfs.github.com/spec/v1
+oid sha256:158129d3b4ecfa65618c0a3ddbaed7c61852041f8478b59a391c451df92039e0
 size 345095797