LexcentraAI/lex-cross-encoder-mbert-5neg-no-eval

lex-cross-encoder-mdeberta-v3-base-5neg

This model is a fine-tuned version of microsoft/mdeberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6811
• Precision: 0.2
• Recall: 1.0
• F2: 0.5556

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-06
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 64
• total_eval_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F2
0.7455	1.0	1	0.6810	0.2	1.0	0.5556
0.7455	2.0	2	0.6811	0.2	1.0	0.5556

Framework versions

• Transformers 4.39.1
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.15.2