sts_nli_roberta-large_lr1e-05_wd1e-03_ep3_lr1e-05_wd1e-03_ep4_ckpt

This model is a fine-tuned version of ys7yoo/nli_roberta-large_lr1e-05_wd1e-03_ep3 on the klue dataset. It achieves the following results on the evaluation set:

• Loss: 0.3223
• Mse: 0.3223
• Mae: 0.4149
• R2: 0.8524

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: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Mse	Mae	R2
0.9853	1.0	183	0.4953	0.4953	0.5298	0.7732
0.1304	2.0	366	0.3296	0.3296	0.4323	0.8491
0.0956	3.0	549	0.3286	0.3286	0.4159	0.8496
0.0751	4.0	732	0.3223	0.3223	0.4149	0.8524

Framework versions

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