ft_da_distilbert_gdp

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: 0.0005
• Mape: 0.7853
• Rmse: 0.0215

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	25	0.0005	0.6568	0.0221
No log	2.0	50	0.0008	1.2260	0.0282
No log	3.0	75	0.0005	0.8126	0.0219
No log	4.0	100	0.0005	0.7617	0.0215
No log	5.0	125	0.0005	0.7150	0.0221
No log	6.0	150	0.0005	0.9076	0.0234
No log	7.0	175	0.0005	0.7852	0.0217
No log	8.0	200	0.0006	1.0439	0.0254
No log	9.0	225	0.0005	0.8113	0.0218
No log	10.0	250	0.0005	0.7853	0.0215

Framework versions

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