ft_da_distilbert_effective_rate

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: 0.0625
• Mape: 21050161102848.0
• Rmse: 0.2500

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	0.0634	7549680615424.0	0.2519
No log	2.0	210	0.0625	21050161102848.0	0.2500
No log	3.0	315	0.0651	15955784630272.0	0.2552
No log	4.0	420	0.0676	16507671150592.0	0.2599
0.0129	5.0	525	0.0729	35525666799616.0	0.2700
0.0129	6.0	630	0.0669	30705371316224.0	0.2586
0.0129	7.0	735	0.0686	32481740849152.0	0.2619
0.0129	8.0	840	0.0703	40486999949312.0	0.2652
0.0129	9.0	945	0.0708	35813152784384.0	0.2661
0.005	10.0	1050	0.0704	38553111232512.0	0.2653

Framework versions

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