charisgao/wnc-pretrain

pretrain_model

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

• Loss: 0.6409
• Precision: 0.6385
• Recall: 0.6046
• F1: 0.6211
• Accuracy: 0.6354

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: 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
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.6994	0.0061	250	0.6909	0.5946	0.1740	0.2692	0.5296
0.6935	0.0122	500	0.6461	0.6368	0.5923	0.6138	0.6288
0.6862	0.0184	750	0.6710	0.6268	0.6416	0.6341	0.6313
0.6629	0.0245	1000	0.8414	0.5772	0.7777	0.6626	0.6056
0.6729	0.0306	1250	0.6509	0.6373	0.5992	0.6177	0.6306

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3