yemen2016/MeMo-BERT-WSD_old

MeMo Model (Word Sense Disambiguation)

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: 0.7214
• F1-score: 0.6667

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	11	0.7214	0.6667
No log	2.0	22	1.2543	0.5429
No log	3.0	33	1.0829	0.6837
No log	4.0	44	1.3815	0.7552
No log	5.0	55	1.4733	0.7005
No log	6.0	66	2.3876	0.5513
No log	7.0	77	1.3215	0.8004
No log	8.0	88	1.4006	0.7608
No log	9.0	99	1.4862	0.7608
No log	10.0	110	1.4974	0.7608
No log	11.0	121	1.4966	0.7608
No log	12.0	132	1.5040	0.7608
No log	13.0	143	1.5010	0.7608
No log	14.0	154	1.4741	0.7608
No log	15.0	165	1.4507	0.7608
No log	16.0	176	1.4420	0.7608
No log	17.0	187	1.4398	0.7608
No log	18.0	198	1.4426	0.7608
No log	19.0	209	1.4438	0.7608
No log	20.0	220	1.4439	0.7608

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.1