dfm2_FGN

This model is a fine-tuned version of KennethEnevoldsen/dfm-sentence-encoder-large-exp2-no-lang-align on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.1487
• F1-score: 0.8233

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	120	0.5474	0.7676
No log	2.0	240	0.7339	0.7596
No log	3.0	360	0.6433	0.7897
No log	4.0	480	0.9757	0.8049
0.4762	5.0	600	1.2749	0.7930
0.4762	6.0	720	1.0429	0.8197
0.4762	7.0	840	1.2813	0.7794
0.4762	8.0	960	1.1487	0.8233
0.0694	9.0	1080	1.4694	0.8015
0.0694	10.0	1200	1.5677	0.7864
0.0694	11.0	1320	1.4541	0.7916
0.0694	12.0	1440	1.4474	0.7941
0.0235	13.0	1560	1.4064	0.7958
0.0235	14.0	1680	1.4497	0.8008
0.0235	15.0	1800	1.3708	0.8058
0.0235	16.0	1920	1.4052	0.8058
0.0122	17.0	2040	1.3883	0.8115
0.0122	18.0	2160	1.4286	0.8126
0.0122	19.0	2280	1.4478	0.8066
0.0122	20.0	2400	1.4547	0.8066

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1