distilbert-finetuned-lr1e-05-epochs15

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: 3.0019

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: 15

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	10	4.0327
No log	2.0	20	3.3750
No log	3.0	30	3.2252
No log	4.0	40	3.0340
No log	5.0	50	2.9771
No log	6.0	60	2.9568
No log	7.0	70	2.9837
No log	8.0	80	2.9969
No log	9.0	90	2.8922
No log	10.0	100	2.9075
No log	11.0	110	2.9617
No log	12.0	120	2.9936
No log	13.0	130	2.9937
No log	14.0	140	2.9997
No log	15.0	150	3.0019

Framework versions

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