README.md

metadata

library_name: transformers
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: videomae-base-videoMAE
    results: []

videomae-base-videoMAE

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: 0.0000
• Accuracy: 1.0
• Precision: 1.0
• Recall: 1.0
• F1: 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: 12850

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.5601	1.0	515	0.4608	1.0	1.0	1.0	1.0
0.6361	2.0	1030	2.9149	0.0	0.0	0.0	0.0
0.1473	3.0	1545	0.0617	1.0	1.0	1.0	1.0
0.0012	4.0	2060	0.0004	1.0	1.0	1.0	1.0
0.096	5.0	2575	0.0004	1.0	1.0	1.0	1.0
0.1104	6.0	3090	0.0003	1.0	1.0	1.0	1.0
0.2175	7.0	3605	2.6599	0.6667	1.0	0.6667	0.8000
0.0004	8.0	4120	0.0003	1.0	1.0	1.0	1.0
0.1348	9.0	4635	0.0011	1.0	1.0	1.0	1.0
0.0001	10.0	5150	0.0001	1.0	1.0	1.0	1.0
0.1291	11.0	5665	0.0001	1.0	1.0	1.0	1.0
0.174	12.0	6180	0.0002	1.0	1.0	1.0	1.0
0.0002	13.0	6695	0.0019	1.0	1.0	1.0	1.0
0.0001	14.0	7210	0.0000	1.0	1.0	1.0	1.0
0.0	15.0	7725	0.0000	1.0	1.0	1.0	1.0
0.0	16.0	8240	0.0000	1.0	1.0	1.0	1.0
0.0	17.0	8755	0.0000	1.0	1.0	1.0	1.0
0.0	18.0	9270	0.0000	1.0	1.0	1.0	1.0
0.0	19.0	9785	0.0000	1.0	1.0	1.0	1.0
0.0	20.0	10300	0.0000	1.0	1.0	1.0	1.0
0.0	21.0	10815	0.0000	1.0	1.0	1.0	1.0
0.0	22.0	11330	0.0000	1.0	1.0	1.0	1.0
0.0	23.0	11845	0.0000	1.0	1.0	1.0	1.0
0.0	24.0	12360	0.0000	1.0	1.0	1.0	1.0
0.0	24.9515	12850	0.0000	1.0	1.0	1.0	1.0

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1