Matcha_clips_224_fintuned_4

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

• Loss: 1.3148
• Accuracy: 0.6951

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 1150

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.7589	0.1	115	1.4438	0.5244
0.8991	1.1	230	1.0762	0.6220
0.2382	2.1	345	0.9143	0.6951
0.1739	3.1	460	1.1205	0.6585
0.0291	4.1	575	1.1838	0.7195
0.0048	5.1	690	1.1936	0.7073
0.0009	6.1	805	1.2866	0.6951
0.0007	7.1	920	1.3004	0.6951
0.0007	8.1	1035	1.3122	0.6951
0.0006	9.1	1150	1.3148	0.6951

Framework versions

• Transformers 4.51.3
• Pytorch 2.3.1+cu121
• Datasets 3.6.0
• Tokenizers 0.21.1