PlacidWombat/stress_roBERTa_classifier

Model Overview

This model is a fine-tuned version of mental/mental-roberta-base finetuned on the dreaddit dataset which is used to classify stress. It achieves the following results on the validation set:

• Loss: 0.5040
• F1 Score: 0.8571

When used on an unseen test set, it achieves an F1 score of 0.839 for 369 Stressed datapoints and 0.813 for 346 Non-Stressed datapoints.

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: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	142	0.3467	0.8505
No log	2.0	284	0.3997	0.8455
No log	3.0	426	0.5040	0.8571

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2