End of training

README.md

@@ -3,6 +3,8 @@ license: cc-by-nc-4.0
 base_model: facebook/timesformer-base-finetuned-k600
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: model_timesformer_subset_01
   results: []
@@ -15,12 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/timesformer-base-finetuned-k600](https://huggingface.co/facebook/timesformer-base-finetuned-k600) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 3.0706
-- eval_accuracy: 0.0665
-- eval_runtime: 321.0045
-- eval_samples_per_second: 6.23
-- eval_steps_per_second: 0.779
-- step: 0
+- Loss: 1.6112
+- Accuracy: 0.5435
 
 ## Model description
 
@@ -48,6 +46,16 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.1
 - training_steps: 4000
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.0091        | 0.25  | 1000 | 1.8240          | 0.4785   |
+| 1.7196        | 1.25  | 2000 | 1.6658          | 0.515    |
+| 1.5516        | 2.25  | 3000 | 1.6609          | 0.534    |
+| 1.2154        | 3.25  | 4000 | 1.6112          | 0.5435   |
+
+
 ### Framework versions
 
 - Transformers 4.38.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f59ee57b258a6ba03fe4e90da283c83a4f88e2772f94527a3619b92a024ff67
+oid sha256:ca25134597b8d9a43161894df0eee4e693d2853a88ed97753f001315029b16e0
 size 485127632

runs/Mar04_04-31-51_0bcc8a440813/events.out.tfevents.1709526731.0bcc8a440813.34.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f005264bb0cf09fc30bed4a382c392df5b19cab69c4f34b9a1d4425d40a50b03
-size 69898
+oid sha256:5c53d756c7bb3d709266bc21964d85f88459eef8fb24085cc157a21973fbf397
+size 91675