distilbert-finetuned-lr1e-07-epochs25

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: 5.4974

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: 25

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	10	6.3781
No log	2.0	20	6.2766
No log	3.0	30	6.1849
No log	4.0	40	6.1020
No log	5.0	50	6.0250
No log	6.0	60	5.9616
No log	7.0	70	5.9008
No log	8.0	80	5.8449
No log	9.0	90	5.7978
No log	10.0	100	5.7540
No log	11.0	110	5.7150
No log	12.0	120	5.6789
No log	13.0	130	5.6482
No log	14.0	140	5.6217
No log	15.0	150	5.5974
No log	16.0	160	5.5775
No log	17.0	170	5.5601
No log	18.0	180	5.5449
No log	19.0	190	5.5323
No log	20.0	200	5.5215
No log	21.0	210	5.5128
No log	22.0	220	5.5062
No log	23.0	230	5.5013
No log	24.0	240	5.4983
No log	25.0	250	5.4974

Framework versions

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