gmra_model_distilbert-base-uncased-distilled-squad_17082023T151553

This model is a fine-tuned version of distilbert-base-uncased-distilled-squad on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4453
• Accuracy: 93.84885764499121%
• F1: 0.9505

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• 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	Accuracy	F1
No log	1.0	284	0.3755	87.5219683655536%	0.8548
0.462	2.0	568	0.2464	92.1792618629174%	0.9384
0.462	3.0	852	0.3129	92.88224956063269%	0.9402
0.1115	4.0	1137	0.3364	93.23374340949033%	0.9492
0.1115	5.0	1421	0.3840	93.58523725834797%	0.9531
0.0445	6.0	1705	0.4202	93.93673110720563%	0.9514
0.0445	7.0	1989	0.4128	93.7609841827768%	0.9538
0.0176	8.0	2274	0.4336	93.84885764499121%	0.9544
0.0084	9.0	2558	0.4445	93.7609841827768%	0.9538
0.0084	9.99	2840	0.4453	93.84885764499121%	0.9505

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1
• Datasets 2.14.4
• Tokenizers 0.13.2