distilbert-base-uncased-finetuned-squad

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 4.1676

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: 2e-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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	47	3.7022
No log	2.0	94	3.2578
No log	3.0	141	3.1677
No log	4.0	188	3.1411
No log	5.0	235	3.2288
No log	6.0	282	3.2640
No log	7.0	329	3.3689
No log	8.0	376	3.4776
No log	9.0	423	3.5919
No log	10.0	470	3.6319
2.2819	11.0	517	3.8199
2.2819	12.0	564	3.9339
2.2819	13.0	611	3.9348
2.2819	14.0	658	3.9293
2.2819	15.0	705	4.0312
2.2819	16.0	752	4.1651
2.2819	17.0	799	4.0788
2.2819	18.0	846	4.1112
2.2819	19.0	893	4.1513
2.2819	20.0	940	4.1676

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0