chaojiang06/arXivEdits-intention-classifier-T5-base-coarse

Checkpoints for arXivEdits paper. Please see more details at the github repo.

arXivEdits-intention-classifier-T5-base-coarse

This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1624
• Accuracy: 0.8242

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: 5e-05
• train_batch_size: 12
• eval_batch_size: 12
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	105	0.3739	0.3470
No log	2.0	210	0.2931	0.4680
No log	3.0	315	0.2312	0.6119
No log	4.0	420	0.1784	0.6918
0.4892	5.0	525	0.1675	0.7648
0.4892	6.0	630	0.1615	0.7763
0.4892	7.0	735	0.1554	0.7900
0.4892	8.0	840	0.1699	0.8105
0.4892	9.0	945	0.1734	0.8151
0.1412	10.0	1050	0.1624	0.8242

Framework versions

• Transformers 4.17.0
• Pytorch 1.11.0+cu113
• Datasets 1.17.0
• Tokenizers 0.11.6