distilbert-base-multilingual-cased_regression_finetuned_mobile01_all

This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.8877
• Mse: 0.8877
• Mae: 0.5973
• Rmse: 0.9422
• Mape: inf
• R Squared: 0.5145

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: 3e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 778
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Mse	Mae	Rmse	Mape	R Squared
1.0906	1.0	7789	1.0449	1.0449	0.7032	1.0222	inf	0.4285
0.9156	2.0	15578	0.9369	0.9369	0.6340	0.9679	inf	0.4875
0.6858	3.0	23367	0.9153	0.9153	0.6189	0.9567	inf	0.4993
1.0272	4.0	31156	0.8877	0.8877	0.5973	0.9422	inf	0.5145
0.7273	5.0	38945	0.8928	0.8928	0.6004	0.9449	inf	0.5117
0.8211	6.0	46734	0.8880	0.8880	0.5936	0.9423	inf	0.5143

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.1
• Datasets 2.18.0
• Tokenizers 0.15.2