distilbert-finetuned-lr1e-06-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: 4.6132

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-06
• 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	5.6593
No log	2.0	20	5.2648
No log	3.0	30	5.0527
No log	4.0	40	4.9205
No log	5.0	50	4.8196
No log	6.0	60	4.7436
No log	7.0	70	4.6878
No log	8.0	80	4.6452
No log	9.0	90	4.6218
No log	10.0	100	4.6132

Framework versions

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