xnli_en_lora_alpha_64_drop_0.1_rank_32_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: 0.5020
• Accuracy: 0.8333

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
0.5372	1.0	12272	0.4704	0.8116
0.4973	2.0	24544	0.4570	0.8229
0.4697	3.0	36816	0.5207	0.7964
0.4701	4.0	49088	0.4386	0.8321
0.4416	5.0	61360	0.4514	0.8337
0.4247	6.0	73632	0.4658	0.8277
0.3972	7.0	85904	0.4697	0.8189
0.3952	8.0	98176	0.4589	0.8257
0.3866	9.0	110448	0.4621	0.8301
0.3498	10.0	122720	0.4718	0.8289
0.3415	11.0	134992	0.4857	0.8229
0.3234	12.0	147264	0.4505	0.8382
0.314	13.0	159536	0.4905	0.8317
0.2895	14.0	171808	0.4851	0.8309
0.2762	15.0	184080	0.5020	0.8333

Framework versions

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