roberta-large-anion.train.no.negation.true.irrelevant1e-06-64

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

• Loss: 0.3497

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: 256
• eval_batch_size: 1024
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
0.6614	1.0	358	0.5283
0.4963	2.0	716	0.4320
0.4477	3.0	1074	0.4129
0.4248	4.0	1432	0.3977
0.413	5.0	1790	0.3897
0.4008	6.0	2148	0.3858
0.3957	7.0	2506	0.3790
0.3879	8.0	2864	0.3749
0.3811	9.0	3222	0.3709
0.3782	10.0	3580	0.3672
0.3748	11.0	3938	0.3650
0.3677	12.0	4296	0.3658
0.3663	13.0	4654	0.3605
0.3617	14.0	5012	0.3638
0.3586	15.0	5370	0.3605
0.3546	16.0	5728	0.3583
0.3512	17.0	6086	0.3549
0.3522	18.0	6444	0.3545
0.3454	19.0	6802	0.3531
0.3472	20.0	7160	0.3526
0.3456	21.0	7518	0.3532
0.3412	22.0	7876	0.3517
0.3402	23.0	8234	0.3505
0.3385	24.0	8592	0.3485
0.336	25.0	8950	0.3494
0.3353	26.0	9308	0.3512
0.3339	27.0	9666	0.3497

Framework versions

• Transformers 4.51.2
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1