lora_alpha_64_drop_0.3_rank_32_seed_42_merges_140_07062024

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: 0.4736
• Accuracy: 0.8321

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: 25.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3419	1.0	12272	0.4769	0.8269
0.3446	2.0	24544	0.4870	0.8273
0.3388	3.0	36816	0.4780	0.8269
0.3458	4.0	49088	0.4691	0.8289
0.3344	5.0	61360	0.4742	0.8337
0.3343	6.0	73632	0.4878	0.8317
0.3173	7.0	85904	0.4847	0.8269
0.333	8.0	98176	0.4779	0.8333
0.3386	9.0	110448	0.4955	0.8293
0.3175	10.0	122720	0.4738	0.8305
0.3175	11.0	134992	0.4895	0.8277
0.3093	12.0	147264	0.4975	0.8309
0.3049	13.0	159536	0.5098	0.8289
0.2994	14.0	171808	0.4855	0.8321
0.3026	15.0	184080	0.5141	0.8289
0.3019	16.0	196352	0.4981	0.8297
0.3129	17.0	208624	0.5032	0.8309
0.3121	18.0	220896	0.5104	0.8281
0.3179	19.0	233168	0.4946	0.8293
0.3416	20.0	245440	0.4951	0.8305
0.3401	21.0	257712	0.4786	0.8289
0.3508	22.0	269984	0.4746	0.8305
0.3425	23.0	282256	0.4736	0.8293
0.3432	24.0	294528	0.4752	0.8313
0.3391	25.0	306800	0.4736	0.8321

Framework versions

• PEFT 0.11.1
• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.18.0
• Tokenizers 0.19.1