mvit_v1_b_transf_c_rwf2000

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6310
• Accuracy: 0.6
• F1: 0.5949
• Precision: 0.6053

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 2850

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision
0.7632	0.0667	190	0.7135	0.475	0.3593	0.4099
0.7848	1.0667	380	0.6864	0.575	0.5467	0.6
0.712	2.0667	570	0.6801	0.6188	0.6133	0.6258
0.6699	3.0667	760	0.6467	0.6625	0.6591	0.6693
0.6366	4.0667	950	0.7547	0.5437	0.4719	0.5959
0.7712	5.0667	1140	0.6155	0.6562	0.6502	0.6678
0.6199	6.0667	1330	0.6310	0.6	0.5949	0.6053

Framework versions

• Transformers 4.44.2
• Pytorch 2.0.1+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1