memobert3_ED

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: 0.7895
• F1-score: 0.9012

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	0.4129	0.8180
No log	2.0	138	0.5440	0.8511
No log	3.0	207	0.6458	0.8767
No log	4.0	276	0.6689	0.8683
No log	5.0	345	0.7171	0.8848
No log	6.0	414	1.0837	0.8585
No log	7.0	483	0.7652	0.8848
0.1451	8.0	552	0.7895	0.9012
0.1451	9.0	621	0.8248	0.8929
0.1451	10.0	690	0.8456	0.8929
0.1451	11.0	759	0.8626	0.8929
0.1451	12.0	828	0.8791	0.8929
0.1451	13.0	897	0.8929	0.8845
0.1451	14.0	966	0.9028	0.8845
0.0001	15.0	1035	0.9134	0.8845
0.0001	16.0	1104	0.9205	0.8845
0.0001	17.0	1173	0.9262	0.8845
0.0001	18.0	1242	0.9309	0.8845
0.0001	19.0	1311	0.9331	0.8845
0.0001	20.0	1380	0.9337	0.8845

Framework versions

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