all-MiniLM-L6-v2-finetuned-marc-en

This model is a fine-tuned version of sentence-transformers/all-MiniLM-L6-v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.8379
• Mae: 2.1394

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: 1e-05
• train_batch_size: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Mae
1.9203	1.0	250	1.8916	2.2446
1.8419	2.0	500	1.8713	2.2371
1.8385	3.0	750	1.8523	2.1957
1.8256	4.0	1000	1.8422	2.1584
1.7618	5.0	1250	1.8339	2.1625
1.8025	6.0	1500	1.8326	2.1564
1.7414	7.0	1750	1.8329	2.1629
1.7539	8.0	2000	1.8322	2.173
1.7886	9.0	2250	1.8290	2.16
1.7611	10.0	2500	1.8292	2.1456
1.7339	11.0	2750	1.8324	2.1566
1.7093	12.0	3000	1.8366	2.1406
1.7164	13.0	3250	1.8371	2.1391
1.6847	14.0	3500	1.8389	2.139
1.7202	15.0	3750	1.8379	2.1394

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1