intent_classification_model_roberta

This model is a fine-tuned version of FacebookAI/xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0233
• Accuracy: 0.9966

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: 2e-05
• train_batch_size: 24
• eval_batch_size: 24
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.6634	0.3680	712	0.7704	0.8192
1.4557	0.7359	1424	0.3484	0.9357
0.8559	1.1039	2136	0.2281	0.9451
0.7125	1.4718	2848	0.1856	0.9506
0.6141	1.8398	3560	0.1342	0.9625
0.5507	2.2078	4272	0.1166	0.9675
0.4741	2.5757	4984	0.0879	0.9758
0.4507	2.9437	5696	0.0634	0.9847
0.397	3.3116	6408	0.0749	0.9797
0.3525	3.6796	7120	0.0616	0.9834
0.3465	4.0475	7832	0.0443	0.9874
0.2644	4.4155	8544	0.0493	0.9859
0.2758	4.7835	9256	0.0395	0.9893
0.2839	5.1514	9968	0.0539	0.9827
0.2045	5.5194	10680	0.0296	0.9923
0.2013	5.8873	11392	0.0218	0.9946
0.169	6.2553	12104	0.0275	0.9934
0.1676	6.6233	12816	0.0255	0.9935
0.1743	6.9912	13528	0.0227	0.9944
0.1216	7.3592	14240	0.0262	0.9935
0.1295	7.7271	14952	0.0243	0.9945
0.133	8.0951	15664	0.0204	0.9957
0.1035	8.4630	16376	0.0234	0.9954
0.1053	8.8310	17088	0.0285	0.9933
0.0987	9.1990	17800	0.0264	0.9952
0.0841	9.5669	18512	0.0202	0.9966
0.0798	9.9349	19224	0.0232	0.9957
0.0812	10.3028	19936	0.0173	0.9967
0.0701	10.6708	20648	0.0216	0.9965
0.0678	11.0388	21360	0.0173	0.9969
0.0504	11.4067	22072	0.0208	0.9959
0.0521	11.7747	22784	0.0227	0.9960
0.0592	12.1426	23496	0.0247	0.9960
0.0364	12.5106	24208	0.0211	0.9967
0.0378	12.8786	24920	0.0201	0.9966
0.0298	13.2465	25632	0.0202	0.9967
0.0286	13.6145	26344	0.0220	0.9967
0.0322	13.9824	27056	0.0193	0.9970
0.0207	14.3504	27768	0.0212	0.9964
0.0274	14.7183	28480	0.0257	0.9961
0.0201	15.0863	29192	0.0211	0.9971
0.0143	15.4543	29904	0.0245	0.9966
0.0168	15.8222	30616	0.0242	0.9965
0.021	16.1902	31328	0.0216	0.9966
0.0097	16.5581	32040	0.0223	0.9968
0.0172	16.9261	32752	0.0210	0.9967
0.0146	17.2941	33464	0.0224	0.9967
0.0125	17.6620	34176	0.0237	0.9966
0.0086	18.0300	34888	0.0232	0.9965
0.0077	18.3979	35600	0.0224	0.9969
0.0037	18.7659	36312	0.0235	0.9964
0.0046	19.1339	37024	0.0223	0.9965
0.0038	19.5018	37736	0.0232	0.9966
0.0058	19.8698	38448	0.0233	0.9966

Framework versions

• Transformers 4.41.2
• Pytorch 2.0.0+cu117
• Datasets 2.20.0
• Tokenizers 0.19.1