Model save

README.md

@@ -3,6 +3,8 @@ license: cc-by-nc-4.0
 base_model: MCG-NJU/videomae-base
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: videomae-base-finetuned-ucf101-subset
   results: []
@@ -14,6 +16,9 @@ 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 unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3096
+- Accuracy: 0.8968
 
 ## Model description
 
@@ -33,13 +38,23 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 1
+- eval_batch_size: 1
 - seed: 42
 - 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: 1200
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.6027        | 0.25  | 300  | 1.3451          | 0.4286   |
+| 1.8979        | 1.25  | 600  | 1.2638          | 0.6286   |
+| 0.5134        | 2.25  | 900  | 0.9131          | 0.7857   |
+| 0.8759        | 3.25  | 1200 | 0.4428          | 0.8857   |
+
 
 ### Framework versions
 

runs/Mar08_07-37-15_1adc69e8f849/events.out.tfevents.1709884404.1adc69e8f849.721.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae56424a9d45ccdbf6c1aeac7a9ce4b6591761871868db4b62cb22c4488a6872
+size 411