ft-videomae-ucf101

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on the aisuko/funsd-layoutlmv3 dataset. It achieves the following results on the evaluation set:

Loss: 0.0175
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: 4
eval_batch_size: 4
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: 150
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2154	0.5	75	0.1093	0.9857
0.0519	1.5	150	0.0175	1.0

Framework versions

Transformers 4.35.2
Pytorch 2.0.0
Datasets 2.1.0
Tokenizers 0.15.0

Downloads last month: 12

Safetensors

Model size

86.2M params

Tensor type

F32

Inference Providers NEW

Video Classification

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Rathgrith/ft-videomae-ucf101

Base model

MCG-NJU/videomae-base-finetuned-kinetics

Finetuned

(279)

this model