sts_nli_klue_roberta_large_lr1e_05_wd1e_03_lr1e-05_wd1e-03_ep5_ckpt

This model is a fine-tuned version of ys7yoo/nli_klue_roberta_large_lr1e-05_wd1e-03 on the klue dataset. It achieves the following results on the evaluation set:

• Loss: 0.3169
• Mse: 0.3169
• Mae: 0.4090
• R2: 0.8549

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-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Mse	Mae	R2
1.1893	1.0	183	0.5904	0.5904	0.5827	0.7296
0.1418	2.0	366	0.4095	0.4095	0.4737	0.8125
0.0967	3.0	549	0.3657	0.3657	0.4383	0.8326
0.0752	4.0	732	0.3391	0.3391	0.4254	0.8447
0.06	5.0	915	0.3169	0.3169	0.4090	0.8549

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu117
• Datasets 2.13.0
• Tokenizers 0.13.3