distilbert-finetuned-lr1e-05-epochs10

This model is a fine-tuned version of distilbert-base-cased-distilled-squad on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.9712

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: 1e-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
No log	1.0	10	4.0485
No log	2.0	20	3.4030
No log	3.0	30	3.2467
No log	4.0	40	3.0756
No log	5.0	50	2.9987
No log	6.0	60	2.9775
No log	7.0	70	2.9824
No log	8.0	80	3.0044
No log	9.0	90	2.9833
No log	10.0	100	2.9712

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3