teacher_mvit_v2_s_CrossEntropyLoss_pretrained_RWF2000-YOLO

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

• Loss: 0.2556
• Accuracy: 0.9158
• F1: 0.9158
• Precision: 0.9158

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
• lr_scheduler_warmup_steps: 144
• training_steps: 1440
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision
0.6495	2.0028	144	0.5515	0.8719	0.8718	0.8725
0.4357	4.0056	288	0.3043	0.9050	0.9050	0.9050
0.2834	6.0083	432	0.2366	0.9132	0.9132	0.9147
0.221	8.0104	576	0.2206	0.9174	0.9174	0.9174
0.1948	10.0118	720	0.2096	0.9298	0.9297	0.9305
0.1426	12.0139	864	0.1927	0.9421	0.9421	0.9426
0.1346	14.0167	1008	0.1938	0.9339	0.9338	0.9358
0.1011	16.0194	1152	0.1861	0.9463	0.9463	0.9466
0.0875	18.0229	1296	0.1950	0.9421	0.9421	0.9423

Framework versions

• Transformers 4.45.2
• Pytorch 2.0.1+cu118
• Datasets 3.0.1
• Tokenizers 0.20.0