dzoQAmodel-roberta

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

• Loss: 8.0177

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: 15

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	16	6.4991
No log	2.0	32	7.0012
No log	3.0	48	6.9841
No log	4.0	64	7.6236
No log	5.0	80	7.3322
No log	6.0	96	7.2519
No log	7.0	112	7.4417
No log	8.0	128	7.9194
No log	9.0	144	8.1410
No log	10.0	160	7.9317
No log	11.0	176	8.0517
No log	12.0	192	7.8702
No log	13.0	208	8.1337
No log	14.0	224	8.0041
No log	15.0	240	8.0177

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1