yemen2016/dfm_ED2

dfm_ED1

This model is a fine-tuned version of KennethEnevoldsen/dfm-sentence-encoder-large on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5402
• F1-score: 0.9344

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	0.3134	0.9098
No log	2.0	138	0.4634	0.8843
No log	3.0	207	0.5135	0.9097
No log	4.0	276	0.4919	0.9179
No log	5.0	345	0.6858	0.8768
No log	6.0	414	0.8026	0.8843
No log	7.0	483	0.5402	0.9344
0.156	8.0	552	0.6149	0.9180
0.156	9.0	621	0.6310	0.9180
0.156	10.0	690	0.6423	0.9180
0.156	11.0	759	0.6514	0.9180
0.156	12.0	828	0.6594	0.9180
0.156	13.0	897	0.6656	0.9180
0.156	14.0	966	0.6712	0.9180
0.0	15.0	1035	0.6755	0.9180
0.0	16.0	1104	0.6792	0.9180
0.0	17.0	1173	0.6824	0.9180
0.0	18.0	1242	0.6844	0.9180
0.0	19.0	1311	0.6856	0.9180
0.0	20.0	1380	0.6861	0.9180

Framework versions

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