MeMo_BERT-SA_1

This model is a fine-tuned version of MiMe-MeMo/MeMo-BERT-01 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.1432
• F1-score: 0.5216

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	297	1.0214	0.4174
1.0021	2.0	594	1.0031	0.4947
1.0021	3.0	891	1.1432	0.5216
0.7732	4.0	1188	1.5043	0.4980
0.7732	5.0	1485	2.0586	0.4878
0.5308	6.0	1782	1.9069	0.4611
0.4125	7.0	2079	2.4514	0.4807
0.4125	8.0	2376	2.7144	0.4941
0.2539	9.0	2673	2.7355	0.5074
0.2539	10.0	2970	3.4404	0.5034
0.1538	11.0	3267	3.6571	0.4976
0.107	12.0	3564	3.8279	0.4992
0.107	13.0	3861	3.8366	0.4825
0.0402	14.0	4158	4.1133	0.4942
0.0402	15.0	4455	4.2386	0.4851
0.0434	16.0	4752	4.4226	0.4938
0.0127	17.0	5049	4.5016	0.5051
0.0127	18.0	5346	4.5485	0.5000
0.0064	19.0	5643	4.6323	0.4810
0.0064	20.0	5940	4.6424	0.4885

Framework versions

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