Model save

README.md

@@ -3,6 +3,8 @@ license: cc-by-nc-4.0
 base_model: facebook/timesformer-base-finetuned-k400
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: timesformer-base-finetuned-k400-kinetic400-subset-epoch6real-num_frame_10_myViT_more_data
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # timesformer-base-finetuned-k400-kinetic400-subset-epoch6real-num_frame_10_myViT_more_data
 
 This model is a fine-tuned version of [facebook/timesformer-base-finetuned-k400](https://huggingface.co/facebook/timesformer-base-finetuned-k400) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1983
+- Accuracy: 0.93
 
 ## Model description
 
@@ -41,6 +46,18 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.1
 - training_steps: 1500
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.2314        | 0.17  | 250  | 0.1349          | 0.96     |
+| 0.6133        | 1.17  | 500  | 0.4123          | 0.92     |
+| 0.0002        | 2.17  | 750  | 0.2224          | 0.95     |
+| 0.0022        | 3.17  | 1000 | 0.1911          | 0.96     |
+| 0.0002        | 4.17  | 1250 | 0.2174          | 0.96     |
+| 0.0002        | 5.17  | 1500 | 0.2116          | 0.96     |
+
+
 ### Framework versions
 
 - Transformers 4.38.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30730170cd1c27b23c2fbeb20577e979592ccab27c7ef8c28c329dd2f5249607
+oid sha256:4a81b3fa21b6ad71efe00fbb22745afd85e0b275321b967217c0e75300c6cdd1
 size 485087636

runs/Apr07_14-08-50_1f81c9d5db56/events.out.tfevents.1712501535.1f81c9d5db56.1667.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9dce7777bb1b4cf39923fed75b47090244425ac395bd696c8ad00788a58f39
+size 10711