README.md

metadata

tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: training_outputs
    results: []

training_outputs

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0394
• Accuracy: 0.993
• Precision: 0.9913
• Recall: 0.9884
• F1: 0.9899
• Roc Auc: 0.9988

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Roc Auc
0.045	0.1105	1000	0.0609	0.987	0.9798	0.9827	0.9812	0.9990
0.0539	0.2210	2000	0.0471	0.988	0.9883	0.9769	0.9826	0.9985
0.0467	0.3316	3000	0.0546	0.989	0.9855	0.9827	0.9841	0.9989
0.0439	0.4421	4000	0.0416	0.99	0.9884	0.9827	0.9855	0.9990
0.0419	0.5526	5000	0.0470	0.99	0.9855	0.9855	0.9855	0.9991
0.0395	0.6631	6000	0.0396	0.992	0.9884	0.9884	0.9884	0.9970
0.0329	0.7737	7000	0.0427	0.993	0.9885	0.9913	0.9899	0.9986
0.0373	0.8842	8000	0.0408	0.992	0.9884	0.9884	0.9884	0.9988
0.031	0.9947	9000	0.0394	0.993	0.9913	0.9884	0.9899	0.9988

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1