klue-sroberta-base-continue-learning-by-mnr

This model is a fine-tuned version of bespin-global/klue-sroberta-base-continue-learning-by-mnr on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1892

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
4.3729	1.0	68	4.2196
4.024	2.0	136	3.6878
3.433	3.0	204	3.0879
2.9423	4.0	272	2.5783
2.361	5.0	340	2.1306
1.8922	6.0	408	1.7540
1.6961	7.0	476	1.4740
1.4765	8.0	544	1.1773
1.3676	9.0	612	0.9409
1.0795	10.0	680	0.7687
0.9284	11.0	748	0.6190
0.6903	12.0	816	0.5083
0.7517	13.0	884	0.4213
0.652	14.0	952	0.3639
0.3433	15.0	1020	0.3037
0.4135	16.0	1088	0.2615
0.2747	17.0	1156	0.2295
0.2824	18.0	1224	0.2061
0.234	19.0	1292	0.1940
0.262	20.0	1360	0.1892

Framework versions

• Transformers 4.46.2
• Pytorch 2.4.0+cu121
• Datasets 2.19.0
• Tokenizers 0.20.3