Edit model card

vivit-b-16x2-kinetics400-finetuned-0512-original

This model is a fine-tuned version of google/vivit-b-16x2-kinetics400 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9100
  • Accuracy: 0.82

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: 1500

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.5879 0.1 150 1.4047 0.54
0.5048 1.1 300 0.7097 0.78
0.1226 2.1 450 0.7969 0.8
0.004 3.1 600 0.9451 0.77
0.0027 4.1 750 0.7712 0.8
0.0011 5.1 900 0.9800 0.8
0.0155 6.1 1050 0.9160 0.8
0.001 7.1 1200 0.9038 0.82
0.0008 8.1 1350 0.8959 0.82
0.2194 9.1 1500 0.9100 0.82

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
10
Safetensors
Model size
88.7M params
Tensor type
F32
ยท
Inference API
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for mlnha/vivit-b-16x2-kinetics400-finetuned-original

Finetuned
(48)
this model

Collection including mlnha/vivit-b-16x2-kinetics400-finetuned-original