chaojiang06/arXivEdits-intention-classifier-T5-base-fine-grained

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

arXivEdits-intention-classifier-T5-base-fine-grained

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

• Loss: 0.1457
• Accuracy: 0.6826

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	0.3043	0.2991
No log	2.0	210	0.2653	0.3311
No log	3.0	315	0.2475	0.4726
No log	4.0	420	0.1737	0.6096
0.5112	5.0	525	0.1660	0.6256
0.5112	6.0	630	0.1499	0.6575
0.5112	7.0	735	0.1497	0.6438
0.5112	8.0	840	0.1457	0.6826
0.5112	9.0	945	0.1470	0.6781
0.151	10.0	1050	0.1428	0.6781

Framework versions

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