End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 0.4431
+- Loss: 0.4379
 - Accuracy: 0.8182
 
 ## Model description
@@ -44,16 +44,17 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 112
+- training_steps: 140
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.7586        | 0.26  | 29   | 0.9480          | 0.6364   |
-| 0.4057        | 1.26  | 58   | 1.0741          | 0.7273   |
-| 0.1479        | 2.26  | 87   | 0.4383          | 0.8182   |
-| 0.0165        | 3.22  | 112  | 0.4431          | 0.8182   |
+| 0.7789        | 0.21  | 29   | 0.7013          | 0.8182   |
+| 0.0557        | 1.21  | 58   | 1.4558          | 0.6364   |
+| 0.2449        | 2.21  | 87   | 0.4050          | 0.8182   |
+| 0.2604        | 3.21  | 116  | 0.3058          | 0.8182   |
+| 0.1159        | 4.17  | 140  | 0.4379          | 0.8182   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61441889f64f5ee550ac0b7adbd2871307d4ee2effc73adb036071ae42072e82
+oid sha256:da593195df252d3ac2165ac4976e010e7c096a2fb185df78c8404d73d7e86b85
 size 485075332