causal_classifier_base_2025c

This model is a fine-tuned version of klue/roberta-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6414
• Accuracy: 0.9251

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: 168
• eval_batch_size: 168
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	339	0.4245	0.8417
0.5717	2.0	678	0.3516	0.8701
0.3813	3.0	1017	0.3092	0.8840
0.3813	4.0	1356	0.3161	0.8891
0.2684	5.0	1695	0.3021	0.9103
0.2029	6.0	2034	0.2936	0.9116
0.2029	7.0	2373	0.3112	0.9149
0.1481	8.0	2712	0.3429	0.9120
0.1194	9.0	3051	0.3431	0.9132
0.1194	10.0	3390	0.3844	0.9124
0.095	11.0	3729	0.3938	0.9132
0.0783	12.0	4068	0.4065	0.9116
0.0783	13.0	4407	0.4191	0.9179
0.0652	14.0	4746	0.3936	0.9226
0.0552	15.0	5085	0.4240	0.9204
0.0552	16.0	5424	0.4168	0.9217
0.0496	17.0	5763	0.4421	0.9226
0.0397	18.0	6102	0.4664	0.9149
0.0397	19.0	6441	0.4536	0.9162
0.0377	20.0	6780	0.4750	0.9175
0.0312	21.0	7119	0.5142	0.9145
0.0312	22.0	7458	0.4935	0.9238
0.027	23.0	7797	0.5284	0.9179
0.0253	24.0	8136	0.5294	0.9204
0.0253	25.0	8475	0.4935	0.9179
0.0223	26.0	8814	0.5449	0.9192
0.0202	27.0	9153	0.6081	0.9120
0.0202	28.0	9492	0.5758	0.9166
0.0175	29.0	9831	0.5966	0.9226
0.0166	30.0	10170	0.5709	0.9230
0.0149	31.0	10509	0.5763	0.9179
0.0149	32.0	10848	0.5613	0.9234
0.0131	33.0	11187	0.5542	0.9242
0.0112	34.0	11526	0.6261	0.9149
0.0112	35.0	11865	0.5678	0.9226
0.0099	36.0	12204	0.5906	0.9192
0.0101	37.0	12543	0.5952	0.9213
0.0101	38.0	12882	0.6016	0.9204
0.0081	39.0	13221	0.6165	0.9200
0.0082	40.0	13560	0.5943	0.9187
0.0082	41.0	13899	0.6079	0.9200
0.0057	42.0	14238	0.6279	0.9209
0.006	43.0	14577	0.6562	0.9209
0.006	44.0	14916	0.6350	0.9221
0.0043	45.0	15255	0.6414	0.9251
0.0038	46.0	15594	0.6516	0.9204
0.0038	47.0	15933	0.6512	0.9221
0.0039	48.0	16272	0.6617	0.9221
0.0043	49.0	16611	0.6699	0.9196
0.0043	50.0	16950	0.6736	0.9196

Framework versions

• Transformers 4.28.1
• Pytorch 2.4.1+cu121
• Datasets 2.21.0
• Tokenizers 0.13.3