memobert3_ED3

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: 0.4675
• 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1-score
No log	1.0	69	0.3591	0.8668
No log	2.0	138	0.4894	0.8582
No log	3.0	207	0.4675	0.9098
No log	4.0	276	0.7260	0.8759
No log	5.0	345	0.6480	0.8924
No log	6.0	414	0.6232	0.9013
No log	7.0	483	0.7043	0.8927
0.1549	8.0	552	0.7174	0.8927
0.1549	9.0	621	0.7093	0.8927
0.1549	10.0	690	0.6832	0.9013

Framework versions

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