Cognitive-Distortions-modern-bert-large-v1

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

• Loss: 3.1055
• Precision: 0.0140
• Recall: 0.0779
• F1: 0.0191

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	2.1875	0.2428	0.2853	0.1608
No log	2.0	26	2.0254	0.4980	0.3765	0.3632
No log	3.0	39	1.8613	0.5207	0.4412	0.3915
No log	4.0	52	1.4053	0.7135	0.5941	0.5789
No log	5.0	65	2.4980	0.4215	0.3206	0.2988
No log	6.0	78	3.1055	0.0140	0.0779	0.0191

Framework versions

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