dfm_ED

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: 0.6486
• F1-score: 0.9180

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	0.4303	0.8683
No log	2.0	138	0.5203	0.8442
No log	3.0	207	0.6280	0.8926
No log	4.0	276	0.6846	0.9003
No log	5.0	345	0.7642	0.9014
No log	6.0	414	0.8076	0.9014
No log	7.0	483	0.8324	0.9014
0.1316	8.0	552	0.8670	0.9010
0.1316	9.0	621	1.2453	0.8499
0.1316	10.0	690	0.6486	0.9180
0.1316	11.0	759	1.1641	0.8671
0.1316	12.0	828	0.8504	0.9097
0.1316	13.0	897	0.8590	0.9096
0.1316	14.0	966	0.8651	0.9096
0.0051	15.0	1035	0.8829	0.8934
0.0051	16.0	1104	0.9813	0.8848
0.0051	17.0	1173	0.9844	0.8848
0.0051	18.0	1242	0.9857	0.8848
0.0051	19.0	1311	0.9858	0.8848
0.0051	20.0	1380	0.9859	0.8848

Framework versions

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