CS505-NerCOQE-xlm-Object

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

• Loss: 0.0005
• F1: 0.9960

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: 16
• eval_batch_size: 16
• 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	F1
No log	1.0	53	0.0870	0.7335
No log	2.0	106	0.1278	0.4618
No log	3.0	159	0.0428	0.8256
No log	4.0	212	0.0307	0.8946
No log	5.0	265	0.0202	0.9143
No log	6.0	318	0.0137	0.9355
No log	7.0	371	0.0093	0.9518
No log	8.0	424	0.0076	0.9686
No log	9.0	477	0.0064	0.9793
No log	10.0	530	0.0031	0.9832
No log	11.0	583	0.0024	0.9773
No log	12.0	636	0.0055	0.9735
No log	13.0	689	0.0027	0.9842
No log	14.0	742	0.0090	0.9091
No log	15.0	795	0.0012	0.9921
No log	16.0	848	0.0007	0.9970
No log	17.0	901	0.0005	0.9960
No log	18.0	954	0.0007	0.9960
No log	19.0	1007	0.0005	0.9960
No log	20.0	1060	0.0005	0.9960

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2