README.md

metadata

library_name: transformers
license: cc-by-nc-4.0
base_model: DaliaSherman/videomae-base-finetuned-beilinson-6epochs
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: videomae-base-finetuned-beilinson-9epochs
    results: []

videomae-base-finetuned-beilinson-9epochs

This model is a fine-tuned version of DaliaSherman/videomae-base-finetuned-beilinson-6epochs on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.9951
• Accuracy: 0.4292

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 156

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8878	0.3333	52	2.2399	0.3734
0.8784	1.3333	104	2.0912	0.4120
1.0743	2.3333	156	1.9951	0.4292

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3