ft_da_distilbert_cpi

This model is a fine-tuned version of gc394/da_distilbert on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0000
• Mape: 2.0758
• Rmse: 0.0048

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: 2e-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: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Mape	Rmse
No log	1.0	105	0.0001	3.3966	0.0073
No log	2.0	210	0.0000	2.7221	0.0055
No log	3.0	315	0.0000	5.1021	0.0063
No log	4.0	420	0.0000	3.3576	0.0053
0.0004	5.0	525	0.0000	2.0579	0.0050
0.0004	6.0	630	0.0000	3.7841	0.0053
0.0004	7.0	735	0.0000	2.3032	0.0049
0.0004	8.0	840	0.0000	3.3604	0.0050
0.0004	9.0	945	0.0000	2.0758	0.0048
0.0001	10.0	1050	0.0000	1.9946	0.0048

Framework versions

• Transformers 4.40.1
• Pytorch 2.4.0.dev20240502
• Datasets 2.19.0
• Tokenizers 0.19.1