profesor_MViT_O_RWF2000

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

• Loss: 0.2973
• Accuracy: 0.9237
• F1: 0.9237
• Precision: 0.9252
• Recall: 0.9237
• Roc Auc: 0.9762

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: 225
• training_steps: 2250
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc
0.4841	2.0324	225	0.3886	0.8947	0.8947	0.8947	0.8947	0.9512
0.2697	5.0311	450	0.2617	0.9158	0.9157	0.9175	0.9158	0.9655
0.1796	8.0298	675	0.2392	0.9184	0.9184	0.9190	0.9184	0.9725
0.1444	11.0284	900	0.2590	0.9184	0.9184	0.9187	0.9184	0.9755
0.1296	14.0271	1125	0.2587	0.9211	0.9210	0.9218	0.9211	0.9738
0.0952	17.0258	1350	0.2924	0.9211	0.9208	0.9258	0.9211	0.9719
0.1148	20.0244	1575	0.2497	0.9263	0.9263	0.9264	0.9263	0.9777
0.0969	23.0231	1800	0.2806	0.9289	0.9289	0.9304	0.9289	0.9775
0.0696	26.0218	2025	0.3203	0.9263	0.9263	0.9267	0.9263	0.9771
0.0915	29.0204	2250	0.3062	0.9263	0.9263	0.9263	0.9263	0.9740

Framework versions

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