distilbert-finetuned-lr1e-07-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: 5.7865

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: 15

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	10	6.3794
No log	2.0	20	6.2819
No log	3.0	30	6.1965
No log	4.0	40	6.1216
No log	5.0	50	6.0546
No log	6.0	60	6.0016
No log	7.0	70	5.9531
No log	8.0	80	5.9108
No log	9.0	90	5.8776
No log	10.0	100	5.8491
No log	11.0	110	5.8264
No log	12.0	120	5.8084
No log	13.0	130	5.7962
No log	14.0	140	5.7891
No log	15.0	150	5.7865

Framework versions

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