yadvender12
/

AV_MAE_task2_8_DF1M

Video Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

yadvender12 commited on May 31

Commit

8600736

•

1 Parent(s): 0b35177

Model save

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -14,11 +14,11 @@ should probably proofread and complete it, then remove this comment. -->
 # AV_MAE_task2_8_DF1M
-This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3676
-- Accuracy: 0.8919
-- F1: 0.8830
 ## Model description
@@ -44,14 +44,14 @@ 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: 18792
 - mixed_precision_training: Native AMP
 ### Training results
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
-| 0.3847        | 1.0   | 18792 | 0.3676          | 0.8919   | 0.8830 |
 ### Framework versions

 # AV_MAE_task2_8_DF1M
+This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.3903
+- Accuracy: 0.8924
+- F1: 0.8831
 ## Model description
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
+- training_steps: 13750
 - mixed_precision_training: Native AMP
 ### Training results
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
+| 0.3724        | 1.0   | 13750 | 0.3903          | 0.8924   | 0.8831 |
 ### Framework versions