teacher_mvit_v2_s_pretrained_True_RWF2000

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

• Loss: 0.2623
• Accuracy: 0.9113
• F1: 0.9112
• Precision: 0.9124

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: 20
• eval_batch_size: 20
• 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
0.6682	0.0507	77	0.6420	0.7937	0.7931	0.7975
0.5711	1.05	153	0.5441	0.8438	0.8437	0.8438
0.477	2.05	229	0.4189	0.8812	0.8812	0.8818
0.3538	3.05	305	0.3375	0.8875	0.8875	0.8877
0.3039	4.05	381	0.2847	0.9	0.9000	0.9003
0.2467	5.05	457	0.2619	0.9125	0.9122	0.9190
0.2965	6.05	533	0.2357	0.9313	0.9310	0.9368
0.221	7.05	609	0.2221	0.925	0.9250	0.9253
0.2071	8.05	685	0.2173	0.925	0.9248	0.9293
0.2129	9.05	761	0.2116	0.9187	0.9187	0.9193
0.2148	10.05	837	0.2107	0.925	0.9248	0.9293
0.1725	11.05	913	0.2085	0.9313	0.9312	0.9329

Framework versions

• Transformers 4.45.1
• Pytorch 2.0.1+cu118
• Datasets 3.0.1
• Tokenizers 0.20.0