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

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

arXivEdits-intention-classifier-T5-large-coarse

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

• Loss: 0.1871
• Accuracy: 0.8607

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	0.3619	0.3699
No log	2.0	210	0.1750	0.7352
No log	3.0	315	0.1416	0.7922
No log	4.0	420	0.1225	0.8425
0.3579	5.0	525	0.1310	0.8516
0.3579	6.0	630	0.1358	0.8425
0.3579	7.0	735	0.1605	0.8493
0.3579	8.0	840	0.1871	0.8607
0.3579	9.0	945	0.1990	0.8516
0.054	10.0	1050	0.2134	0.8607

Framework versions

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