Cognitive-Distortions-roberta-large-v1

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

• Loss: 2.4961
• Precision: 0.0056
• Recall: 0.075
• F1: 0.0105

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: 5e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• optimizer: Use adamw_torch_fused 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: 500
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
No log	1.0	13	2.3555	0.0424	0.2059	0.0703
No log	2.0	26	2.1992	0.1517	0.3015	0.1963
No log	3.0	39	2.4004	0.0899	0.2574	0.1322
No log	4.0	52	2.4961	0.0056	0.075	0.0105

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.1+cu128
• Datasets 4.4.1
• Tokenizers 0.22.1