lora_alpha_64_drop_0.3_rank_32_seed_42_merges_10_06062024

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: 0.4904
• Accuracy: 0.8382

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: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5609	1.0	12272	0.5028	0.8064
0.531	2.0	24544	0.4831	0.8100
0.5012	3.0	36816	0.5365	0.7928
0.5058	4.0	49088	0.4832	0.8189
0.4843	5.0	61360	0.4514	0.8297
0.4713	6.0	73632	0.4654	0.8225
0.4482	7.0	85904	0.4776	0.8064
0.4547	8.0	98176	0.4771	0.8261
0.4421	9.0	110448	0.4794	0.8201
0.416	10.0	122720	0.4620	0.8305
0.4197	11.0	134992	0.4913	0.8153
0.3948	12.0	147264	0.4439	0.8309
0.3942	13.0	159536	0.4618	0.8341
0.3763	14.0	171808	0.4574	0.8345
0.3667	15.0	184080	0.5019	0.8317
0.3598	16.0	196352	0.4770	0.8341
0.3557	17.0	208624	0.4867	0.8341
0.3362	18.0	220896	0.4725	0.8390
0.3166	19.0	233168	0.4828	0.8378
0.3158	20.0	245440	0.4904	0.8382

Framework versions

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