sts_nli_roberta-large_lr1e-05_wd1e-03_ep3_lr1e-05_wd1e-03_ep3_ckpt

This model was trained from scratch on the klue dataset. It achieves the following results on the evaluation set:

• Loss: 0.3260
• Mse: 0.3260
• Mae: 0.4173
• R2: 0.8507

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Mse	Mae	R2
0.9158	1.0	183	0.4483	0.4483	0.4964	0.7947
0.1335	2.0	366	0.3875	0.3875	0.4620	0.8226
0.0964	3.0	549	0.3260	0.3260	0.4173	0.8507

Framework versions

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