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-epoch6-num_frame_10_myViT2window4_more_data_b4
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # timesformer-base-finetuned-k400-kinetic400-subset-epoch6-num_frame_10_myViT2window4_more_data_b4
 
 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: 0.1876
+- Accuracy: 0.96
 
 ## Model description
 
@@ -41,6 +46,18 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.1
 - training_steps: 72
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.407         | 0.18  | 13   | 0.6302          | 0.92     |
+| 0.2401        | 1.18  | 26   | 0.2320          | 0.96     |
+| 0.0568        | 2.18  | 39   | 0.1465          | 0.96     |
+| 0.0045        | 3.18  | 52   | 0.1131          | 0.96     |
+| 0.0027        | 4.18  | 65   | 0.1251          | 0.92     |
+| 0.0022        | 5.1   | 72   | 0.1256          | 0.92     |
+
+
 ### Framework versions
 
 - Transformers 4.38.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a9fb117907a15c51ee7e9eaa5b14dc27b847eea902f694bd582d2893702c3cc
+oid sha256:2a38e861bf1dd2dd4641ac6b073a5668ff7daf62b667515c5e3e371a7c9127a5
 size 485087636

runs/Apr21_09-03-43_6cf390ac2b33/events.out.tfevents.1713690724.6cf390ac2b33.8244.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8782b919f9ba7a3e822865adb36a74f33f745262944fcf763913cda2f591caef
+size 1112