timesformer-base-finetuned-k400-finetuned-kinetic400-epoch6-num_frame_10_TimeSformer_more_data

This model is a fine-tuned version of facebook/timesformer-base-finetuned-k400 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1021
  • Accuracy: 0.97

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: 1
  • eval_batch_size: 1
  • 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
0.3263 0.17 250 0.1773 0.95
0.367 1.17 500 0.6111 0.91
0.0003 2.17 750 0.3224 0.95
0.0006 3.17 1000 0.2025 0.96
0.0007 4.17 1250 0.0962 0.98
0.0002 5.17 1500 0.1149 0.98

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
12
Safetensors
Model size
121M params
Tensor type
F32
·
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 JackWong0911/timesformer-base-finetuned-k400-finetuned-kinetic400-epoch6-num_frame_10_TimeSformer_more_data

Finetuned
(46)
this model