distilbert-base-multilingual-cased_regression_finetuned_ptt

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: 1.8809
• Mse: 1.8809
• Mae: 1.0160
• Rmse: 1.3715
• Mape: inf
• R Squared: 0.0000

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: 206
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Mse	Mae	Rmse	Mape	R Squared
1.9028	1.0	2062	1.8809	1.8809	1.0147	1.3715	inf	0.0000
1.9381	2.0	4124	1.8831	1.8831	1.0177	1.3723	inf	-0.0011
1.8691	3.0	6186	1.8809	1.8809	1.0160	1.3715	inf	0.0000
1.7741	4.0	8248	1.8809	1.8809	1.0153	1.3715	inf	0.0000
1.6734	5.0	10310	1.8809	1.8809	1.0143	1.3715	inf	0.0000

Framework versions

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