xnli_en_adalora_alpha_64_drop_0.2_rank_32_seed_456

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

• Loss: 0.4225
• Accuracy: 0.8394

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: 0.0003
• train_batch_size: 32
• eval_batch_size: 8
• seed: 456
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5434	1.0	12272	0.4738	0.8129
0.5139	2.0	24544	0.4917	0.8112
0.4951	3.0	36816	0.4466	0.8257
0.4705	4.0	49088	0.4194	0.8386
0.446	5.0	61360	0.4156	0.8345
0.4327	6.0	73632	0.4357	0.8301
0.4274	7.0	85904	0.4331	0.8273
0.4112	8.0	98176	0.4198	0.8365
0.4119	9.0	110448	0.4282	0.8357
0.4026	10.0	122720	0.4334	0.8357
0.3926	11.0	134992	0.4224	0.8382
0.3924	12.0	147264	0.4163	0.8462
0.3858	13.0	159536	0.4340	0.8345
0.3723	14.0	171808	0.4192	0.8394
0.3829	15.0	184080	0.4225	0.8394

Framework versions

• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.18.0
• Tokenizers 0.19.1