memo3_NC

This model is a fine-tuned version of MiMe-MeMo/MeMo-BERT-03 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.9917
• F1-score: 0.7193

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: 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-score
No log	1.0	74	0.5188	0.6932
No log	2.0	148	0.5211	0.6932
No log	3.0	222	0.6723	0.6793
No log	4.0	296	1.1152	0.6731
No log	5.0	370	1.5249	0.6865
No log	6.0	444	1.6461	0.7127
0.2853	7.0	518	1.9231	0.6997
0.2853	8.0	592	1.9948	0.6997
0.2853	9.0	666	1.8700	0.7096
0.2853	10.0	740	1.9034	0.6929
0.2853	11.0	814	2.1139	0.6997
0.2853	12.0	888	2.0404	0.7158
0.2853	13.0	962	1.9917	0.7193
0.0105	14.0	1036	2.1849	0.6939
0.0105	15.0	1110	2.1404	0.7035
0.0105	16.0	1184	2.1241	0.7035
0.0105	17.0	1258	2.1735	0.7035
0.0105	18.0	1332	2.1518	0.7035
0.0105	19.0	1406	2.1672	0.7035
0.0105	20.0	1480	2.1628	0.7035

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1