xnli_en_adalora_alpha_32_drop_0.1_rank_16_seed_42

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: 0.4247
• Accuracy: 0.8361

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: 42
• 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
0.554	1.0	12272	0.5014	0.7980
0.5077	2.0	24544	0.4857	0.8108
0.4793	3.0	36816	0.5534	0.7767
0.4791	4.0	49088	0.4443	0.8225
0.4541	5.0	61360	0.4434	0.8257
0.4405	6.0	73632	0.4273	0.8325
0.4208	7.0	85904	0.4405	0.8313
0.4278	8.0	98176	0.4376	0.8297
0.422	9.0	110448	0.4329	0.8337
0.4085	10.0	122720	0.4296	0.8402
0.396	11.0	134992	0.4348	0.8333
0.3909	12.0	147264	0.4250	0.8357
0.3956	13.0	159536	0.4289	0.8382
0.3792	14.0	171808	0.4236	0.8365
0.3759	15.0	184080	0.4247	0.8361

Framework versions

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