student_videomobilevit_not_learning_RWF2000

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

• Loss: 0.6661
• Accuracy: 0.77
• F1: 0.7689
• Precision: 0.7750

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: 180
• training_steps: 1800
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision
0.5117	2.02	180	0.4612	0.7844	0.7841	0.7857
0.3803	4.04	360	0.4049	0.8156	0.8150	0.8201
0.3181	7.02	540	0.4287	0.8	0.7989	0.8069
0.2548	9.04	720	0.4230	0.8094	0.8080	0.8184
0.2348	12.02	900	0.3655	0.85	0.85	0.85
0.1722	14.04	1080	0.3827	0.8594	0.8594	0.8595
0.1861	17.02	1260	0.4371	0.8562	0.8562	0.8571
0.1753	19.04	1440	0.4214	0.8438	0.8435	0.8457
0.1464	22.02	1620	0.5414	0.8438	0.8427	0.8531
0.1411	24.04	1800	0.4668	0.8531	0.8530	0.8542

Framework versions

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