destilbert_uncased_fever_nli

This model is a fine-tuned version of distilbert-base-uncased on a subset of fever_nli dataset by using the first 7.5k datapoints per each label from the training split. It achieves the following results on the evaluation set:

• Loss: 2.1829
• F1: 0.7045

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: 0.0001
• train_batch_size: 64
• eval_batch_size: 64
• 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	F1
No log	1.0	352	0.7894	0.7029
0.5462	2.0	704	0.9908	0.7097
0.2922	3.0	1056	1.0831	0.6924
0.2922	4.0	1408	1.2833	0.7044
0.142	5.0	1760	1.4096	0.7008
0.0695	6.0	2112	1.5585	0.7013
0.0695	7.0	2464	1.7262	0.7015
0.0434	8.0	2816	2.0138	0.7016
0.0204	9.0	3168	2.0912	0.7012
0.011	10.0	3520	2.1829	0.7045

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.1+cu116
• Datasets 2.8.0
• Tokenizers 0.13.2