profesor_MViT_O_RLVS

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

• Loss: 0.0329
• Accuracy: 0.9921
• F1: 0.9921
• Precision: 0.9922
• Recall: 0.9921
• Roc Auc: 0.9997

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 237
• training_steps: 2370
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc
0.4418	2.0325	237	0.2877	0.9464	0.9464	0.9477	0.9464	0.9917
0.1303	5.0312	474	0.1071	0.9705	0.9705	0.9709	0.9705	0.9984
0.0767	8.0300	711	0.0454	0.9946	0.9946	0.9946	0.9946	0.9998
0.0628	11.0287	948	0.0341	0.9946	0.9946	0.9947	0.9946	0.9994
0.0381	14.0274	1185	0.0157	0.9973	0.9973	0.9973	0.9973	1.0
0.0328	17.0262	1422	0.0202	0.9946	0.9946	0.9947	0.9946	0.9999
0.0276	20.0249	1659	0.0447	0.9866	0.9866	0.9869	0.9866	1.0000
0.0497	23.0236	1896	0.0289	0.9946	0.9946	0.9947	0.9946	0.9997

Framework versions

• Transformers 4.46.1
• Pytorch 2.0.1+cu118
• Datasets 3.0.2
• Tokenizers 0.20.1