estudiante_MC318_profesor_MViT_akl_RWF2000

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

• Loss: 0.2574
• Accuracy: 0.8975
• F1: 0.8975
• Precision: 0.8981
• Recall: 0.8975
• Roc Auc: 0.9620

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: 159
• training_steps: 1590
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc
10.7532	1.0145	79	0.5529	0.79	0.7877	0.8034	0.79	0.8806
8.2982	2.0289	158	0.4024	0.825	0.8250	0.8251	0.825	0.9141
6.7699	4.0082	237	0.3657	0.8425	0.8415	0.8509	0.8425	0.9352
5.05	5.0226	316	0.3208	0.8625	0.8620	0.8674	0.8625	0.9438
4.4531	7.0019	395	0.3502	0.855	0.8539	0.8656	0.855	0.9484
3.8667	8.0164	474	0.3259	0.845	0.8434	0.8594	0.845	0.9545
3.4567	9.0308	553	0.3032	0.8675	0.8667	0.8765	0.8675	0.9578
2.922	11.0101	632	0.2989	0.8675	0.8666	0.8778	0.8675	0.9609
2.7125	12.0245	711	0.3040	0.8725	0.8719	0.8794	0.8725	0.9617
2.4511	14.0038	790	0.2715	0.87	0.8692	0.8797	0.87	0.9637
2.3903	15.0182	869	0.2697	0.88	0.8796	0.8856	0.88	0.9647
2.2202	16.0327	948	0.2715	0.88	0.8796	0.8847	0.88	0.9653
2.2101	18.0119	1027	0.2757	0.875	0.8745	0.8814	0.875	0.9662
2.1343	19.0264	1106	0.2397	0.905	0.9050	0.9056	0.905	0.9648
1.8394	21.0057	1185	0.2570	0.865	0.8641	0.8746	0.865	0.9667
1.9406	22.0201	1264	0.2746	0.8825	0.8821	0.8876	0.8825	0.9674
1.7509	23.0346	1343	0.2545	0.89	0.8897	0.8939	0.89	0.9692

Framework versions

• Transformers 4.46.3
• Pytorch 2.0.1+cu118
• Datasets 3.1.0
• Tokenizers 0.20.3