Model save

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: 0.5099
-- Accuracy: 0.8516
+- Loss: 0.4163
+- Accuracy: 0.8581
 
 ## Model description
 
@@ -38,22 +38,20 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 1
-- eval_batch_size: 1
+- train_batch_size: 2
+- eval_batch_size: 2
 - 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: 1200
+- training_steps: 300
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.7089        | 0.25  | 300  | 2.0866          | 0.2143   |
-| 2.0487        | 1.25  | 600  | 1.3321          | 0.5571   |
-| 0.9147        | 2.25  | 900  | 1.0757          | 0.7714   |
-| 0.9604        | 3.25  | 1200 | 0.5315          | 0.8429   |
+| 1.0261        | 0.5   | 150  | 0.9821          | 0.6857   |
+| 0.7237        | 1.5   | 300  | 0.5007          | 0.8286   |
 
 
 ### Framework versions

runs/Mar13_02-55-41_1acbf7fe0677/events.out.tfevents.1710299030.1acbf7fe0677.265.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afad28c73b2fb5c404efcf90ac383145df199ec9c6cfb9058dbf437f604a0c5c
+size 411