End of training

README.md

@@ -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: 0.2276
-- Accuracy: 0.8857
+- Loss: 0.2849
+- Accuracy: 0.9111
 
 ## Model description
 
@@ -42,24 +42,24 @@ The following hyperparameters were used during training:
 - train_batch_size: 3
 - eval_batch_size: 3
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- 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: 400
+- training_steps: 200
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.4185        | 0.25  | 100  | 1.5354          | 0.4143   |
-| 0.4758        | 1.25  | 200  | 0.5897          | 0.7857   |
-| 0.2382        | 2.25  | 300  | 0.3358          | 0.8143   |
-| 0.0981        | 3.25  | 400  | 0.2276          | 0.8857   |
+| 1.188         | 0.25  | 50   | 0.9450          | 0.6222   |
+| 0.6172        | 1.25  | 100  | 0.4384          | 0.8222   |
+| 0.325         | 2.25  | 150  | 0.2533          | 0.8889   |
+| 0.1939        | 3.25  | 200  | 0.2849          | 0.9111   |
 
 
 ### Framework versions
 
-- Transformers 4.44.2
-- Pytorch 2.5.0+cu121
-- Datasets 3.1.0
-- Tokenizers 0.19.1
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu124
+- Datasets 2.21.0
+- Tokenizers 0.20.3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e60af4835ee7fcb0e9a8fc8ea30980117f40bf96745cc609d6c35b16a55af08
+oid sha256:1d3f6f256a4cf9796ce7641d5572d60b344fe513b86ed813d4247542ca1b06d5
 size 344946604