codet5-small-ft-v5

This model is a fine-tuned version of Salesforce/codet5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.2463
• Rouge1: 65.8333
• Rouge2: 56.2963
• Rougel: 65.6481
• Rougelsum: 65.5556
• Gen Len: 12.3333

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	8	3.3878	36.9391	29.7138	36.367	36.2452	16.5278
No log	2.0	16	2.6133	61.7593	52.7981	61.8981	61.3889	12.1111
No log	3.0	24	2.3167	61.0185	51.7328	61.0185	60.5556	11.8611
No log	4.0	32	2.2463	65.8333	56.2963	65.6481	65.5556	12.3333

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0