estudiante_S3D_RLVS

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

• Loss: 0.0544
• Accuracy: 0.9868
• F1: 0.9868
• Precision: 0.9870
• Recall: 0.9868
• Roc Auc: 0.9975

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: 75
• eval_batch_size: 75
• 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: 189
• training_steps: 1890
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc
0.3299	3.0116	94	0.2381	0.9144	0.9142	0.9203	0.9144	0.9785
0.1284	7.0106	188	0.1116	0.9332	0.9331	0.9360	0.9332	0.9897
0.072	11.0095	282	0.0926	0.9626	0.9626	0.9639	0.9626	0.9945
0.046	15.0085	376	0.0669	0.9840	0.9840	0.9840	0.9840	0.9967
0.034	19.0074	470	0.0625	0.9840	0.9840	0.9840	0.9840	0.9968
0.0237	23.0063	564	0.0466	0.9840	0.9840	0.9840	0.9840	0.9968
0.0282	27.0053	658	0.0644	0.9840	0.9840	0.9840	0.9840	0.9965
0.0145	31.0042	752	0.0628	0.9813	0.9813	0.9814	0.9813	0.9967
0.0158	35.0032	846	0.0569	0.9840	0.9840	0.9840	0.9840	0.9964

Framework versions

• Transformers 4.46.1
• Pytorch 2.0.1+cu118
• Datasets 3.1.0
• Tokenizers 0.20.1