asmaa1's picture
Model save
6f582a9
metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: videomae-base-groub2-finetuned-SLT-subset
    results: []

videomae-base-groub2-finetuned-SLT-subset

This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2405
  • Accuracy: 1.0

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: 2
  • eval_batch_size: 2
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • training_steps: 960

Training results

Training Loss Epoch Step Validation Loss Accuracy
3.928 0.06 61 3.6624 0.0244
3.8332 1.06 122 3.5354 0.0732
3.5587 2.06 183 3.2996 0.0976
3.4907 3.06 244 3.1796 0.0976
3.4674 4.06 305 3.1159 0.0976
3.5079 5.06 366 3.0202 0.1220
2.9034 6.06 427 2.8292 0.1707
2.9286 7.06 488 2.4582 0.6098
2.4388 8.06 549 1.8469 0.7317
1.7172 9.06 610 1.2915 0.8537
1.2504 10.06 671 0.8991 0.9512
0.974 11.06 732 0.5943 0.9268
0.4528 12.06 793 0.4040 0.9512
0.3593 13.06 854 0.3052 1.0
0.2068 14.06 915 0.2569 1.0
0.185 15.05 960 0.2405 1.0

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3