SeungHeeKim/deberta-v3-large-cross-exp156

enc_cross_encoder__lr_7e-6__wd_0.1__trans_False__obj_mse__tri_None__s_42

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

• Loss: 0.0917
• Mse: 0.0917
• Pearsonr: 0.4893
• Spearmanr: 0.4924

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: 7e-06
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Mse	Pearsonr	Spearmanr
No log	1.0	354	0.0982	0.0982	0.3975	0.4064
0.1166	2.0	709	0.0880	0.0880	0.4867	0.4889
0.0903	3.0	1062	0.0917	0.0917	0.4893	0.4924

Framework versions

• Transformers 4.37.2
• Pytorch 2.0.1
• Datasets 2.19.1
• Tokenizers 0.15.2