working

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: 4.6095
• Accuracy: 0.0266
• Top 1 Accuracy: 0.0266
• Top 5 Accuracy: 0.0858
• Top 10 Accuracy: 0.1420
• Macro Precision: 0.0024
• Macro Recall: 0.0173
• Macro F1: 0.0039
• Pearson Corr: 0.3016
• Spearman Corr: 0.2739

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
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 900
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Top 1 Accuracy	Top 5 Accuracy	Top 10 Accuracy	Macro Precision	Macro Recall	Macro F1	Pearson Corr	Spearman Corr
4.523	5.0542	500	4.6095	0.0266	0.0266	0.0858	0.1420	0.0024	0.0173	0.0039	0.3016	0.2739

Framework versions

• Transformers 4.44.0
• Pytorch 1.11.0+cu102
• Datasets 2.21.0
• Tokenizers 0.19.1