estudiante_MC318_profesor_MViT_kl_VIOPERU

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

• Loss: 0.5934
• Accuracy: 0.7411
• F1: 0.7385
• Precision: 0.7507
• Recall: 0.7411
• Roc Auc: 0.7864

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: 30
• eval_batch_size: 30
• 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: 21
• training_steps: 210
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc
0.573	1.0095	10	0.6925	0.4821	0.4739	0.4810	0.4821	0.4917
0.5568	2.0190	20	0.6923	0.5893	0.5784	0.5996	0.5893	0.5714
0.5075	3.0286	30	0.6917	0.5893	0.5784	0.5996	0.5893	0.5893
0.4825	4.0381	40	0.6812	0.625	0.6190	0.6333	0.625	0.6173
0.4945	6.0095	50	0.6742	0.6429	0.6387	0.6497	0.6429	0.6193
0.4713	7.0190	60	0.6770	0.6429	0.6387	0.6497	0.6429	0.6416
0.4427	8.0286	70	0.6663	0.6429	0.6387	0.6497	0.6429	0.6569
0.4328	9.0381	80	0.6689	0.6607	0.6580	0.6660	0.6607	0.6645
0.4304	11.0095	90	0.6742	0.625	0.6190	0.6333	0.625	0.6607
0.3899	12.0190	100	0.6754	0.6607	0.6580	0.6660	0.6607	0.6824
0.378	13.0286	110	0.6510	0.6786	0.6769	0.6823	0.6786	0.6735
0.3712	14.0381	120	0.6389	0.6786	0.6769	0.6823	0.6786	0.6747
0.3432	16.0095	130	0.6588	0.6964	0.6956	0.6987	0.6964	0.6824
0.3321	17.0190	140	0.6819	0.6964	0.6956	0.6987	0.6964	0.6849
0.3215	18.0286	150	0.6643	0.6964	0.6956	0.6987	0.6964	0.6983
0.3309	19.0381	160	0.6170	0.6964	0.6956	0.6987	0.6964	0.6964
0.2808	21.0095	170	0.6335	0.6964	0.6956	0.6987	0.6964	0.7028
0.2741	22.0190	180	0.6440	0.7143	0.7139	0.7154	0.7143	0.7092
0.2838	23.0286	190	0.7138	0.6964	0.6956	0.6987	0.6964	0.6990
0.289	24.0381	200	0.6650	0.6964	0.6956	0.6987	0.6964	0.7105
0.2481	26.0095	210	0.6567	0.6964	0.6956	0.6987	0.6964	0.7181

Framework versions

• Transformers 4.46.1
• Pytorch 2.0.1+cu118
• Datasets 3.1.0
• Tokenizers 0.20.2