roberta-base-ppasubj-500000-1e-06-128

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

• Loss: 0.6633

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: 512
• eval_batch_size: 1024
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
0.6886	1.0	977	0.6772
0.6792	2.0	1954	0.6701
0.6753	3.0	2931	0.6673
0.6743	4.0	3908	0.6656
0.6734	5.0	4885	0.6653
0.672	6.0	5862	0.6642
0.6713	7.0	6839	0.6635
0.6705	8.0	7816	0.6634
0.6687	9.0	8793	0.6636
0.6675	10.0	9770	0.6639
0.6664	11.0	10747	0.6632
0.666	12.0	11724	0.6633
0.6652	13.0	12701	0.6631
0.6656	14.0	13678	0.6627
0.6644	15.0	14655	0.6634
0.6627	16.0	15632	0.6637
0.6634	17.0	16609	0.6633

Framework versions

• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1