xnli_en_adalora_alpha_64_drop_0.3_rank_32_seed_123

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: 0.4354
• Accuracy: 0.8414

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: 123
• 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
0.5508	1.0	12272	0.5385	0.7859
0.525	2.0	24544	0.4698	0.8076
0.4908	3.0	36816	0.4830	0.8157
0.4659	4.0	49088	0.4696	0.8165
0.467	5.0	61360	0.4578	0.8189
0.4567	6.0	73632	0.4467	0.8357
0.4349	7.0	85904	0.4480	0.8293
0.4291	8.0	98176	0.4587	0.8249
0.4332	9.0	110448	0.4436	0.8361
0.4176	10.0	122720	0.4434	0.8349
0.4066	11.0	134992	0.4361	0.8329
0.3959	12.0	147264	0.4376	0.8353
0.3911	13.0	159536	0.4237	0.8454
0.3961	14.0	171808	0.4321	0.8422
0.3976	15.0	184080	0.4354	0.8414

Framework versions

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