Model save

README.md

@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # videomae-base-finetuned-ucf101-subset
 
-This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an a small part of RAVDESS dataset.
+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: 2.1335
-- Accuracy: 0.1111
+- Loss: 2.0669
+- Accuracy: 0.2222
 
 ## Model description
 
@@ -50,12 +50,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.5   | 4    | 2.1220          | 0.125    |
-| No log        | 1.5   | 8    | 2.1347          | 0.125    |
+| No log        | 0.5   | 4    | 2.0845          | 0.125    |
+| No log        | 1.5   | 8    | 2.0850          | 0.125    |
 
 
 ### Framework versions
 
 - Transformers 4.34.1
 - Pytorch 2.1.0+cu118
+- Datasets 2.14.6
 - Tokenizers 0.14.1

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:441c53370f1da0e5512d8af510aceb87f2f0f4e8772521965cdbac8c069194c8
+oid sha256:ae0bc5e962a84f057c8dfe4f2befa24ca30ae92b3316a7150d27d043800ba081
 size 345897666