yemen2016/memobert3_ED2

memobert3_ED1

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: 0.6065
• F1-score: 0.9098

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	69	0.3808	0.8439
No log	2.0	138	0.4234	0.8432
No log	3.0	207	0.4577	0.9013
No log	4.0	276	0.6278	0.8851
No log	5.0	345	0.6449	0.8517
No log	6.0	414	0.7495	0.8678
No log	7.0	483	0.6065	0.9098
0.1663	8.0	552	0.6217	0.9098
0.1663	9.0	621	0.6420	0.9098
0.1663	10.0	690	0.6514	0.9098
0.1663	11.0	759	0.6627	0.9098
0.1663	12.0	828	0.6726	0.9098
0.1663	13.0	897	0.6828	0.9016
0.1663	14.0	966	0.6904	0.9016
0.0001	15.0	1035	0.6942	0.9016
0.0001	16.0	1104	0.6976	0.9016
0.0001	17.0	1173	0.7007	0.9016
0.0001	18.0	1242	0.7027	0.9016
0.0001	19.0	1311	0.7038	0.9016
0.0001	20.0	1380	0.7037	0.9016

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1