mvit_v1_rwf-2000

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

• Loss: 0.4447
• Accuracy: 0.8938
• F1: 0.8937
• Precision: 0.8940

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: 2e-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: 1520

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision
0.5548	0.125	190	0.4052	0.875	0.8737	0.8906
0.5137	1.125	380	0.3075	0.8688	0.8681	0.8759
0.3765	2.125	570	0.3078	0.8688	0.8679	0.8788
0.3435	3.125	760	0.2652	0.9125	0.9124	0.9135
0.0875	4.125	950	0.3103	0.9125	0.9124	0.9148
0.3563	5.125	1140	0.3361	0.9187	0.9186	0.9220
0.2176	6.125	1330	0.3506	0.9187	0.9187	0.9204

Framework versions

• Transformers 4.44.0
• Pytorch 2.0.1+cu118
• Datasets 2.20.0
• Tokenizers 0.19.1