distilbert-finetuned-lr1e-07-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: 5.9816

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-07
• 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	6.3810
No log	2.0	20	6.2885
No log	3.0	30	6.2110
No log	4.0	40	6.1465
No log	5.0	50	6.0925
No log	6.0	60	6.0534
No log	7.0	70	6.0217
No log	8.0	80	5.9990
No log	9.0	90	5.9862
No log	10.0	100	5.9816

Framework versions

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